© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25424
    Prev
    Next
    INDEX
    Explanations

    more than one

    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
    soporte
    -1.89
    に来て
    -1.86
    catálogo
    -1.82
    𓁹
    -1.82
    actéristi
    -1.77
    えっ
    -1.72
    もうすぐ
    -1.72
    に行って
    -1.71
     ホルダー
    -1.68
    𖣔
    -1.66
    POSITIVE LOGITS
     of
    3.14
     in
    2.41
    および
    1.60
     makes
    1.59
    ซึ่ง
    1.54
     from
    1.45
     at
    1.45
     подготовка
    1.44
    そして
    1.43
     on
    1.42
    Activations Density 0.033%

    No Known Activations