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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91738
    Prev
    Next
    INDEX
    Explanations

    supernatural powers and abilities

    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
    WEBPACK
    -0.89
    خان
    -0.85
    ßung
    -0.82
    lichung
    -0.79
    tinyos
    -0.78
    opardi
    -0.78
    ientes
    -0.75
     ダイヤモンド
    -0.75
     Ucraina
    -0.75
    Външни
    -0.75
    POSITIVE LOGITS
     abilities
    2.75
     powers
    2.75
     poderes
    2.05
    powers
    1.97
     ability
    1.94
     superpowers
    1.73
     capabilities
    1.63
     power
    1.63
    Powers
    1.60
     gifts
    1.58
    Activations Density 0.030%

    No Known Activations