© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106466
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis then opening brace

    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
    -1.02
     of
    -0.90
     känns
    -0.90
    смотр
    -0.88
     for
    -0.86
     from
    -0.84
    пон
    -0.84
     as
    -0.81
     was
    -0.80
    cides
    -0.79
    POSITIVE LOGITS
    sste
    0.95
    hộp
    0.90
    텐츠
    0.85
    owatt
    0.85
     другая
    0.85
    ANCING
    0.85
    ))){
    0.85
     neumáticos
    0.83
    Bibliografie
    0.83
     wszystkim
    0.83
    Activations Density 0.004%

    No Known Activations