© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8979
    Prev
    Next
    INDEX
    Explanations

    variables and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    </blockquote>
    0.81
    <blockquote>
    0.69
     AsRef
    0.61
    </h3>
    0.57
     হওয়ার
    0.56
     Burnham
    0.55
    pena
    0.55
    원본
    0.54
    렬
    0.52
    假的
    0.52
    POSITIVE LOGITS
     industry
    0.61
    كيت
    0.58
     金
    0.55
    Cher
    0.55
     کشورهای
    0.54
     Industry
    0.53
    िल्म
    0.53
     BEEN
    0.52
     eBooks
    0.52
     Deutsches
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.