© 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. 34-GEMMASCOPE-RES-131K
    7. 47212
    Prev
    Next
    INDEX
    Explanations

    `Virginia`, `John`, `online`, `while`

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    が
    -1.09
    を
    -1.00
    によって
    -0.85
    は
    -0.84
    ...?
    -0.84
    而又
    -0.81
    や
    -0.81
    で
    -0.79
    ㉗
    -0.78
    ?),
    -0.77
    POSITIVE LOGITS
    箩
    1.08
    ࣭
    0.96
    場所に
    0.93
    あぁ
    0.92
    значение
    0.90
    場所で
    0.90
     terkenal
    0.89
    焌
    0.89
     mewakili
    0.89
    やう
    0.88
    Activations Density 0.853%

    No Known Activations