© 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. 79300
    Prev
    Next
    INDEX
    Explanations

    darkly comic and scary drama

    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
    pollution
    -0.80
    ッカ
    -0.77
     conoz
    -0.77
    RETURN
    -0.75
    ды
    -0.72
    aried
    -0.72
     auß
    -0.71
     nifer
    -0.70
     Pollution
    -0.70
    ceras
    -0.69
    POSITIVE LOGITS
     dark
    2.78
    dark
    2.14
     black
    2.14
    DARK
    2.05
     gallows
    2.03
     darkly
    2.00
    Dark
    1.94
     DARK
    1.76
    ブラック
    1.72
    black
    1.67
    Activations Density 0.035%

    No Known Activations