© 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. 79203
    Prev
    Next
    INDEX
    Explanations

    keyboard and mouse input

    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
    ボタン
    -0.96
     балан
    -0.77
     button
    -0.73
     zemi
    -0.72
    MTG
    -0.71
     nebu
    -0.71
    BUTTON
    -0.70
     anima
    -0.70
     buttons
    -0.70
     Button
    -0.69
    POSITIVE LOGITS
    leds
    0.88
     ADB
    0.84
     Caps
    0.80
     toggle
    0.79
     Sticky
    0.77
     repeat
    0.77
     Kensington
    0.77
    rän
    0.77
     led
    0.76
    LED
    0.75
    Activations Density 0.027%

    No Known Activations