© 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. 102365
    Prev
    Next
    INDEX
    Explanations

    run out of

    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
    </em>
    -2.50
    秶
    -2.36
    The
    -2.25
    Thanks
    -2.25
    You
    -2.19
    without
    -2.13
    does
    -2.11
    6
    -2.11
    [
    -2.06
    We
    -2.02
    POSITIVE LOGITS
    
    2.19
    骓
    2.16
    </h1>
    2.03
    皛
    1.93
    
    1.87
     ehemalige
    1.84
    Restrict
    1.83
    犄
    1.82
     perfección
    1.80
    禰
    1.77
    Activations Density 0.002%

    No Known Activations