© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33167
    Prev
    Next
    INDEX
    Explanations

    javascript library urls

    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_22/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
    があり
    -1.91
    がありますが
    -1.90
    を
    -1.89
    などが
    -1.77
    はある
    -1.71
    前は
    -1.71
    日を
    -1.68
    方針
    -1.55
    もありますが
    -1.55
    曲は
    -1.55
    POSITIVE LOGITS
    為に
    2.14
    ようです
    1.86
    んですよ
    1.80
    ようで
    1.73
    ほら
    1.71
    で見る
    1.67
    感じです
    1.64
    のではないか
    1.64
    場所で
    1.64
    様な
    1.63
    Activations Density 0.019%

    No Known Activations