© 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. 21061
    Prev
    Next
    INDEX
    Explanations

    anonymous uploads and feedback

    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
    <bos>
    -2.50
    líben
    -2.16
     policiais
    -2.11
     are
    -2.08
    </h3>
    -2.08
     vali
    -2.06
    -2.03
    很高
    -1.98
    至于
    -1.94
    鞮
    -1.90
    POSITIVE LOGITS
    ↵
    2.73
    ions
    2.22
    ção
    2.05
    鸶
    2.03
    
    1.99
    ify
    1.98
    essment
    1.98
    tocks
    1.98
    '\\
    1.97
    phans
    1.94
    Activations Density 0.003%

    No Known Activations