© 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. 13281
    Prev
    Next
    INDEX
    Explanations

    mapping URLs, emotional connections, dependencies, voltage

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

    The neuron is detecting numeric tokens formatted as floating‐point values (numbers with a decimal point).

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

    whitespace or formatting characters that separate sections or items in technical or structured documents.

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

    mentions of named entities and formal titles—organizations, products, places, awards, and technical specifications.

    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
     ثالث
    0.80
     природных
    0.77
     миллионов
    0.75
    끈
    0.75
    跚
    0.74
     proporción
    0.73
    ▟
    0.73
    uas
    0.72
     viscous
    0.71
    Gruß
    0.70
    POSITIVE LOGITS
     асо
    0.83
    га
    0.81
        
    0.81
     Megh
    0.76
    цо
    0.75
    جتما
    0.74
    ቦ
    0.74
     Aren
    0.74
     đem
    0.73
     evo
    0.73
    Activations Density 0.000%

    No Known Activations