© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    discontinuing service or operation

    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
    籥
    -3.06
    見ても
    -2.55
     his
    -2.53
     Fällen
    -2.53
    ſu
    -2.48
    ⻬
    -2.44
     The
    -2.39
    ⟣
    -2.34
    秾
    -2.34
     也
    -2.33
    POSITIVE LOGITS
    ？！”
    2.88
    谵
    2.73
    ’
    2.67
    d
    2.66
    m
    2.52
    雠
    2.50
    ！！”
    2.44
    k
    2.42
    酲
    2.39
    趼
    2.33
    Activations Density 0.003%

    No Known Activations