© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    on the

    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
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -1.96
    鏽
    -1.71
    遑
    -1.64
     during
    -1.63
     at
    -1.60
     gets
    -1.49
     on
    -1.49
     as
    -1.47
    🌞
    -1.47
     because
    -1.45
    POSITIVE LOGITS
     the
    3.73
     a
    3.23
     semelh
    1.78
    だら
    1.77
     employé
    1.71
    盉
    1.69
     planejamento
    1.69
     artesanato
    1.68
    ༑
    1.67
     contou
    1.65
    Activations Density 0.542%

    No Known Activations