© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72157
    Prev
    Next
    INDEX
    Explanations

    classifies or clasps

    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
    Negative Logits
    髡
    -2.39
    渽
    -2.09
    \
    -2.08
    忉
    -2.06
    茑
    -2.06
    纮
    -2.05
    迳
    -2.03
     rédig
    -2.00
    する
    -2.00
    ᭝
    -1.99
    POSITIVE LOGITS
     are
    3.25
    of
    2.83
     kemudian
    2.31
     Then
    2.31
    ICOLON
    2.30
     prennent
    2.30
     otras
    2.27
    」
    2.25
     atas
    2.23
    aston
    2.23
    Activations Density 0.005%

    No Known Activations