© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22430
    Prev
    Next
    INDEX
    Explanations

    high blood

    np_acts-logits-general · gemini-2.5-flash-lite

    conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    台中
    0.54
     Darth
    0.50
    瑋
    0.48
    橐
    0.48
    ла
    0.48
    хи
    0.48
     jí
    0.47
     Beyoncé
    0.47
    гда
    0.46
    消息
    0.46
    POSITIVE LOGITS
    v
    0.46
    okkh
    0.46
    predictor
    0.45
    OCK
    0.43
    orbidity
    0.43
    ep
    0.43
    änz
    0.43
    bdb
    0.42
    csv
    0.42
    unlist
    0.42
    Activations Density 0.000%

    No Known Activations