© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84575
    Prev
    Next
    INDEX
    Explanations

    delinquent taxes, stealth, location, names, denying, dollar, Police, list

    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
     then
    -2.00
     When
    -1.82
    n
    -1.75
    );
    -1.69
     on
    -1.63
    1
    -1.60
    ).
    -1.59
    h
    -1.52
     devono
    -1.50
    item
    -1.49
    POSITIVE LOGITS
    腟
    1.65
    presumably
    1.63
    sistence
    1.60
    certainly
    1.55
    vádz
    1.54
    地区的
    1.51
    apparently
    1.51
    ympto
    1.48
    虬
    1.48
    퐿
    1.47
    Activations Density 0.120%

    No Known Activations