© 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. 116467
    Prev
    Next
    INDEX
    Explanations

    poker actions

    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
     Wünsche
    -0.81
    liant
    -0.78
     Mahomes
    -0.78
    јани
    -0.76
    ัน
    -0.75
     generar
    -0.74
    toff
    -0.72
    FileInput
    -0.72
    味は
    -0.71
    owali
    -0.71
    POSITIVE LOGITS
     bluff
    1.86
     folding
    1.69
     fold
    1.69
    Fold
    1.63
     Fold
    1.59
     blu
    1.59
     Folding
    1.58
    folding
    1.45
     Bluff
    1.45
     call
    1.39
    Activations Density 0.008%

    No Known Activations