© 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. 10-GEMMASCOPE-RES-131K
    7. 112424
    Prev
    Next
    INDEX
    Explanations

    findings of a

    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_10/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
    ulauan
    -1.98
    '
    -1.83
     MediaQuery
    -1.83
    تیجه
    -1.73
    </i>
    -1.73
    ',
    -1.73
    strictEqual
    -1.71
     maneuver
    -1.66
    ↵
    -1.65
    на
    -1.59
    POSITIVE LOGITS
    所以我
    1.95
    ings
    1.82
     teaming
    1.80
    畊
    1.77
     avaliações
    1.75
    犼
    1.74
    
    1.70
     baseado
    1.68
    鸶
    1.68
    同时也
    1.67
    Activations Density 0.016%

    No Known Activations