© 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. 82755
    Prev
    Next
    INDEX
    Explanations

    fight outcomes and decisions

    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
     intermedia
    -0.81
     sitesinde
    -0.78
    дования
    -0.78
    ladiator
    -0.77
     удовольствием
    -0.77
     prostrate
    -0.76
    lared
    -0.75
    τός
    -0.75
     punches
    -0.73
     compr
    -0.71
    POSITIVE LOGITS
    dropIfExists
    0.81
    elite
    0.81
    iş
    0.81
     xét
    0.80
    زه
    0.79
     concevoir
    0.79
    гар
    0.77
    Said
    0.76
     campanha
    0.76
    ולוג
    0.75
    Activations Density 0.039%

    No Known Activations