© 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. 99406
    Prev
    Next
    INDEX
    Explanations

    expect than suffer

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

    non-english words and numbers

    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
     sickle
    0.45
     abundant
    0.42
     ổ
    0.42
     Lines
    0.41
    মাই
    0.41
     been
    0.39
     alternate
    0.39
     inconspicuous
    0.39
     liens
    0.39
     entraî
    0.39
    POSITIVE LOGITS
     벨
    0.51
    诘
    0.47
     무게
    0.46
    igl
    0.46
    glise
    0.46
    гун
    0.44
    astricht
    0.44
     ঢুক
    0.43
     Леони
    0.43
     عز
    0.43
    Activations Density 0.000%

    No Known Activations