© 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. 32048
    Prev
    Next
    INDEX
    Explanations

    object prototype

    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
    ást
    -0.80
    你也
    -0.79
     spiced
    -0.79
    legi
    -0.78
     Guillaume
    -0.75
     ヴィトン
    -0.75
    ambo
    -0.73
    ype
    -0.72
    خاص
    -0.70
    manjaro
    -0.70
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.99
     
    0.95
    ↵↵↵↵↵↵↵
    0.82
    webp
    0.82
    ↵↵↵↵↵↵↵↵
    0.79
    ↵↵↵↵↵↵
    0.77
    tember
    0.75
    potamus
    0.75
     föres
    0.74
    шники
    0.73
    Activations Density 0.001%

    No Known Activations