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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118630
    Prev
    Next
    INDEX
    Explanations

    Fast 50

    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
    گاری
    -0.80
     couscous
    -0.79
    чество
    -0.78
     ويكي
    -0.75
    폼
    -0.75
     Doodle
    -0.74
     fuq
    -0.74
     عالم
    -0.73
     COACH
    -0.73
     indefinitely
    -0.72
    POSITIVE LOGITS
     fastest
    2.02
     growth
    1.68
     Fastest
    1.65
    Fastest
    1.55
    Growth
    1.55
    growth
    1.53
     Growth
    1.48
    fast
    1.44
     fast
    1.32
     Inc
    1.25
    Activations Density 0.018%

    No Known Activations