© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4146
    Prev
    Next
    INDEX
    Explanations

    sharing information or content

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to the very first content word of a new section or list entry—that is, it flags the leading token in headings or itemized entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    generic boilerplate text or spam content, particularly from low-quality websites and automated content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    prominent single-word keywords in web-style lists, tags, or headlines, especially generic action, industry, or locator terms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gì
    0.73
     hãy
    0.72
    วิน
    0.71
    沌
    0.70
    ار
    0.69
     trùng
    0.69
    Props
    0.68
     اين
    0.68
    ARIA
    0.68
    ไหล
    0.68
    POSITIVE LOGITS
     Canine
    0.92
     lucro
    0.80
     Branding
    0.76
     Stairs
    0.74
     Percolation
    0.70
     pequenas
    0.70
    अ
    0.70
    ्स
    0.69
    igold
    0.69
    ek
    0.68
    Activations Density 0.000%

    No Known Activations