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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67628
    Prev
    Next
    INDEX
    Explanations

    reducer function calls

    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
    y
    -4.81
    啬
    -3.28
    
    -3.19
    
    -3.14
    蹋
    -3.02
    。
    -2.98
    沕
    -2.95
    鲎
    -2.92
    ).
    -2.84
    govor
    -2.83
    POSITIVE LOGITS
    I
    4.25
    er
    3.09
    ه
    3.06
    но
    2.83
    (
    2.75
    Our
    2.61
    *
    2.50
     -
    2.48
     theor
    2.47
    [
    2.38
    Activations Density 0.008%

    No Known Activations