© 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. 114101
    Prev
    Next
    INDEX
    Explanations

    puzzled, baffled, bewildered

    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
     prenda
    -2.17
    細胞
    -2.13
     necessario
    -2.09
     saluti
    -2.03
    ſures
    -2.00
    縂
    -1.98
     lampada
    -1.98
    Ꮟ
    -1.96
     häls
    -1.95
     symbolizes
    -1.92
    POSITIVE LOGITS
    {~
    2.56
    isation
    2.42
    何度
    2.30
    利
    2.09
    挑戦
    2.09
    荻
    2.09
     исчез
    2.08
     الرئيسي
    2.08
    どのような
    2.06
    .
    2.06
    Activations Density 0.006%

    No Known Activations