© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72722
    Prev
    Next
    INDEX
    Explanations

    code structure and imports

    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_22/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
     correcte
    -1.11
    quitos
    -1.07
    "/",
    -1.03
    циональный
    -1.01
    reonine
    -0.98
    蛋糕
    -0.98
    ствую
    -0.96
    anwal
    -0.95
    ntä
    -0.95
    tième
    -0.95
    POSITIVE LOGITS
    ↵↵
    1.38
     Pläne
    1.08
     even
    1.07
     Hinsicht
    0.94
     Herausforderung
    0.90
    ensacola
    0.89
     więc
    0.88
    ेत्र
    0.87
    THURSDAY
    0.85
     hacerlo
    0.85
    Activations Density 0.035%

    No Known Activations