© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60744
    Prev
    Next
    INDEX
    Explanations

    finding function, module, gene, or list indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -3.13
    a
    -3.03
    \
    -2.92
     in
    -2.83
     Since
    -2.72
     FOR
    -2.70
     Combining
    -2.63
     ;
    -2.61
     Knowing
    -2.50
    e
    -2.50
    POSITIVE LOGITS
    CHREIB
    3.63
    噐
    2.89
     ſmall
    2.78
    seems
    2.73
    岽
    2.69
     tivi
    2.63
    眎
    2.63
    踯
    2.63
     endeavours
    2.55
     ‚
    2.50
    Activations Density 0.001%

    No Known Activations