© 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. 61304
    Prev
    Next
    INDEX
    Explanations

    roman numeral IX

    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
    ↵↵
    -3.75
    O
    -3.66
    -
    -2.92
    A
    -2.78
        
    -2.78
    人が
    -2.56
     ,
    -2.56
    ，
    -2.55
    髏
    -2.47
    that
    -2.44
    POSITIVE LOGITS
    哢
    2.86
     This
    2.83
    姤
    2.78
    푢
    2.77
    ⢊
    2.73
    皤
    2.64
    遯
    2.61
    蜮
    2.61
     interrump
    2.59
    趼
    2.55
    Activations Density 0.005%

    No Known Activations