© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118876
    Prev
    Next
    INDEX
    Explanations

    boxing, Canelo, ABCs, operations, Peach Entertainment

    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
     opponents
    -0.85
    練習
    -0.79
     fome
    -0.79
     fname
    -0.77
     preta
    -0.76
     Caus
    -0.75
     advocated
    -0.74
    Conservative
    -0.74
    ہر
    -0.74
     professionals
    -0.73
    POSITIVE LOGITS
    阅
    0.81
     maneuver
    0.80
    )</
    0.78
    = 
    0.77
     ее
    0.76
    choon
    0.75
     gluing
    0.75
     calzado
    0.73
    liday
    0.73
    閱
    0.73
    Activations Density 0.020%

    No Known Activations