© 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. 25292
    Prev
    Next
    INDEX
    Explanations

    programming code keywords and types

    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
     considération
    -0.88
     república
    -0.88
    してました
    -0.85
    ända
    -0.84
    féle
    -0.83
     proceeds
    -0.80
    ůž
    -0.80
     these
    -0.80
    AFFIRMED
    -0.79
    explanation
    -0.78
    POSITIVE LOGITS
    "]["
    0.96
    ₴
    0.96
    再次
    0.95
     kanskje
    0.94
     novamente
    0.91
    }],
    0.91
    allon
    0.90
    ;
    0.90
     gikk
    0.90
     SAL
    0.90
    Activations Density 0.003%

    No Known Activations