© 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. 118925
    Prev
    Next
    INDEX
    Explanations

    documentation syntax

    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
    Paul
    -0.89
     Int
    -0.86
    dex
    -0.85
    mainAxisSize
    -0.81
    رب
    -0.79
    jev
    -0.79
     browsers
    -0.78
     surf
    -0.77
    appcompat
    -0.77
     بھی
    -0.77
    POSITIVE LOGITS
     object
    0.99
     trait
    0.85
    feer
    0.83
    tato
    0.79
    obe
    0.77
    gira
    0.75
     extends
    0.75
     Trait
    0.74
     teilnehmen
    0.72
     convento
    0.72
    Activations Density 0.018%

    No Known Activations