© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124605
    Prev
    Next
    INDEX
    Explanations

    Barrett and Gall

    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
     erhi
    -2.64
    ㌧
    -2.58
    ଽ
    -2.56
    
    -2.53
    
    -2.33
     Improving
    -2.28
     Increases
    -2.27
     extravagance
    -2.27
    不算
    -2.25
    我了
    -2.25
    POSITIVE LOGITS
    }{
    3.22
    </h4>
    2.89
    </sup>
    2.73
    謦
    2.63
    ），
    2.53
    ');
    2.47
    }$,
    2.42
    ">
    2.31
    踯
    2.30
     Mitarbeitern
    2.28
    Activations Density 0.005%

    No Known Activations