© 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. 80795
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     tomaron
    -2.17
     both
    -2.09
    :
    -1.95
    私には
    -1.93
     recibieron
    -1.93
    -
    -1.89
    ;
    -1.88
    私に
    -1.83
     decidieron
    -1.81
     concluyó
    -1.79
    POSITIVE LOGITS
    ↵↵
    2.72
     who
    2.55
    Bissau
    1.98
    ที่
    1.84
    StoryboardSegue
    1.80
    面目
    1.78
    因为
    1.77
    vább
    1.74
    ко
    1.70
     onOptions
    1.69
    Activations Density 1.015%

    No Known Activations