© 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. 108924
    Prev
    Next
    INDEX
    Explanations

    action movie actors and characters

    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
    喹
    -0.76
    agot
    -0.75
     Gwen
    -0.75
    quins
    -0.75
     couch
    -0.73
    lección
    -0.72
    Doktor
    -0.72
    ANDE
    -0.72
    واعد
    -0.71
    tivo
    -0.71
    POSITIVE LOGITS
     action
    1.43
     martial
    1.23
    martial
    1.17
     Action
    1.13
    ACTION
    1.12
    Action
    1.06
    styleable
    0.94
    Martial
    0.94
    アクション
    0.91
    IMF
    0.91
    Activations Density 0.057%

    No Known Activations