© 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. 47324
    Prev
    Next
    INDEX
    Explanations

    radio station frequencies

    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
     NEGRO
    -0.81
    />,
    -0.81
     kurikulum
    -0.77
    unlike
    -0.76
    kate
    -0.75
    ^(@)
    -0.75
     Quintet
    -0.74
    ■■
    -0.72
    %#
    -0.71
    плення
    -0.70
    POSITIVE LOGITS
     midday
    0.74
    uan
    0.73
     euch
    0.71
     ANC
    0.70
     bolt
    0.70
     soy
    0.69
     SIR
    0.69
    似
    0.69
     Official
    0.69
     boron
    0.69
    Activations Density 0.033%

    No Known Activations