© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73888
    Prev
    Next
    INDEX
    Explanations

    paranoid and sabbath

    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
    opress
    -0.84
     Lessing
    -0.77
     Kitt
    -0.77
     presid
    -0.73
     なっ
    -0.72
     Heidegger
    -0.71
     Galen
    -0.70
    kshake
    -0.69
     rebuilding
    -0.68
     dwóch
    -0.68
    POSITIVE LOGITS
     Osbourne
    1.14
     Paran
    0.83
    DARK
    0.82
     paranormal
    0.81
    Sharon
    0.78
    🤘
    0.78
     Worcestershire
    0.77
     Sharon
    0.77
     Adriana
    0.77
     Sabbath
    0.75
    Activations Density 0.011%

    No Known Activations