© 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. 74384
    Prev
    Next
    INDEX
    Explanations

    missing word or data

    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
     {
    -1.72
    ド
    -1.69
     capitaine
    -1.63
    潸
    -1.60
     новой
    -1.60
     ejemplares
    -1.59
     Préférences
    -1.58
    人が
    -1.55
    ぐるみ
    -1.53
    *}[
    -1.52
    POSITIVE LOGITS
     Missing
    1.72
    晅
    1.71
    ).
    1.70
     That
    1.69
     hearty
    1.55
     devise
    1.55
     missing
    1.53
     from
    1.52
     which
    1.45
    的信息
    1.45
    Activations Density 0.019%

    No Known Activations