© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15440
    Prev
    Next
    INDEX
    Explanations

    explaining "why"

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

    The neuron is highly sensitive to spam‐style link and URL patterns (i.e. inline URLs, link markup, or affiliate‐style hyperlinks).

    oai_token-act-pair · o4-miniTriggered 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
    i
    0.94
    ه
    0.80
    '_
    0.79
    aan
    0.78
     LinearLayout
    0.78
     &=&
    0.78
    ah
    0.76
    ound
    0.75
    iiv
    0.74
    oot
    0.72
    POSITIVE LOGITS
     commemor
    0.80
     laparoscopic
    0.79
     scienza
    0.79
     gyne
    0.77
     psychology
    0.77
     commemorating
    0.76
     célébr
    0.75
     pecinta
    0.75
    گ
    0.75
     солдат
    0.75
    Activations Density 0.000%

    No Known Activations