© 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. 188285
    Prev
    Next
    INDEX
    Explanations

    word followed by its associate

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

    processing data status

    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
    Representatives
    0.52
    ﾝ
    0.50
    WELL
    0.48
    ネル
    0.47
    FRONT
    0.47
    बांग
    0.46
    ЛО
    0.46
    ब
    0.45
    SER
    0.45
    am
    0.45
    POSITIVE LOGITS
     festivities
    0.50
     Feh
    0.48
     oeuvre
    0.46
     aftermath
    0.44
     Fallout
    0.44
     случилось
    0.44
     ដ
    0.44
     Cort
    0.43
     StatelessWidget
    0.43
     carefree
    0.43
    Activations Density 0.000%

    No Known Activations