© 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. 86979
    Prev
    Next
    INDEX
    Explanations

    ) followed by operators/keywords

    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
    L
    -2.34
    ;
    -1.95
    หรือ
    -1.83
     poised
    -1.80
    K
    -1.73
     и
    -1.72
    E
    -1.70
     />
    -1.67
    M
    -1.67
    з
    -1.66
    POSITIVE LOGITS
     It
    1.96
    趼
    1.83
    ſures
    1.82
     majesty
    1.80
    
    1.79
    战斗力
    1.75
    焄
    1.73
    </strong>
    1.72
    ⽬
    1.69
    鍆
    1.67
    Activations Density 0.009%

    No Known Activations