© 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. 45382
    Prev
    Next
    INDEX
    Explanations

    id, strategy, asset

    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
    izaron
    -0.86
     jongen
    -0.85
     Abb
    -0.81
    envoyer
    -0.81
     siding
    -0.80
    褴
    -0.80
     difficultés
    -0.78
     Dill
    -0.77
     pistolet
    -0.75
     konkre
    -0.75
    POSITIVE LOGITS
     strategy
    1.27
    strategy
    1.01
     strategies
    0.97
     Strategy
    0.93
     generator
    0.90
    Strategy
    0.88
     type
    0.82
    联
    0.77
    聯
    0.75
     künstler
    0.73
    Activations Density 0.005%

    No Known Activations