© 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. 79244
    Prev
    Next
    INDEX
    Explanations

    Angular component views

    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
     Serge
    -0.82
    说了
    -0.73
    imens
    -0.73
     bilhões
    -0.72
    hereinafter
    -0.72
    Serge
    -0.71
     spout
    -0.70
    ዴ
    -0.70
     Lion
    -0.70
     жесто
    -0.69
    POSITIVE LOGITS
    view
    0.84
    harusnya
    0.83
     reflective
    0.83
    諭
    0.80
    bootstrap
    0.79
    onViewCreated
    0.75
    وزه
    0.75
    பெ
    0.72
    FIC
    0.71
    свя
    0.71
    Activations Density 0.012%

    No Known Activations