© 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. 72608
    Prev
    Next
    INDEX
    Explanations

    html closing tag followed by opening tag

    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
     to
    -1.78
     "";
    -1.78
    ̜
    -1.73
     them
    -1.64
    その
    -1.53
    balon
    -1.51
    penas
    -1.48
    垢
    -1.48
     of
    -1.47
    wallpapers
    -1.47
    POSITIVE LOGITS
    of
    2.05
    殽
    1.84
    ?-
    1.82
    ipzig
    1.74
     スタンド
    1.65
    眼前的
    1.65
    他自己
    1.63
    validate
    1.63
    那人
    1.62
     tradi
    1.61
    Activations Density 0.004%

    No Known Activations