© 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. 85044
    Prev
    Next
    INDEX
    Explanations

    New data or question start

    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
    其他
    -1.94
    },
    -1.70
    其它
    -1.68
    它的
    -1.66
    ,
    -1.63
    ’
    -1.59
    しました
    -1.58
    \
    -1.58
     more
    -1.56
    '
    -1.56
    POSITIVE LOGITS
    .《
    1.87
     
    1.74
    扨
    1.73
    
    1.72
     podjet
    1.70
    
    1.70
    깽
    1.65
    偸
    1.63
     ujar
    1.61
    – 
    1.59
    Activations Density 0.001%

    No Known Activations