© 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. 56653
    Prev
    Next
    INDEX
    Explanations

    report, license, description

    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
    Negative Logits
    endent
    -0.91
    inox
    -0.84
     ity
    -0.82
     Woodrow
    -0.81
    Binance
    -0.80
    ひた
    -0.77
    laka
    -0.73
    resso
    -0.72
    陌生
    -0.72
    Cosmo
    -0.71
    POSITIVE LOGITS
     maybe
    0.85
    ０
    0.82
     on
    0.81
     moderately
    0.81
     fairly
    0.77
    $$
    0.76
    楊
    0.75
    輿
    0.75
    KERN
    0.74
     both
    0.74
    Activations Density 0.013%

    No Known Activations