© 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. 10-GEMMASCOPE-RES-131K
    7. 67827
    Prev
    Next
    INDEX
    Explanations

    names starting with Haw

    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
    ↵
    -2.95
    But
    -2.50
    G
    -2.41
    ’
    -2.41
    出会い
    -2.39
    必要な
    -2.34
    A
    -2.34
     europäischen
    -2.34
    T
    -2.30
    两人的
    -2.28
    POSITIVE LOGITS
    z
    2.53
    捽
    2.53
     グレー
    2.48
    所以我
    2.44
    x
    2.42
     anser
    2.39
    鼇
    2.33
    푏
    2.33
     caters
    2.33
     セックス
    2.33
    Activations Density 0.003%

    No Known Activations