© 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. 66128
    Prev
    Next
    INDEX
    Explanations

    www Facebook handles

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

    continuation and involvement

    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
     getest
    0.42
    getMinutes
    0.41
    WIN
    0.41
     forbid
    0.40
     possiamo
    0.40
    *)
    0.40
    ORES
    0.40
    atoms
    0.40
    மிருந்து
    0.40
    *;
    0.39
    POSITIVE LOGITS
     मार्शल
    0.52
     особенности
    0.49
    rong
    0.49
     জিজ্ঞাসাবাদ
    0.48
    rug
    0.47
     Drexel
    0.45
     ежеднев
    0.45
     технологи
    0.44
     बिक्री
    0.44
     వరకు
    0.44
    Activations Density 0.000%

    No Known Activations