© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108893
    Prev
    Next
    INDEX
    Explanations

    restless boredom or delegative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ale
    0.54
    itted
    0.52
    att
    0.51
    urt
    0.48
    toy
    0.46
    acch
    0.45
    ledge
    0.44
    γ
    0.44
     October
    0.44
    esper
    0.44
    POSITIVE LOGITS
    ométrique
    0.48
    يان
    0.47
    Rüyada
    0.47
    МА
    0.47
    ىز
    0.47
    امي
    0.46
     иденти
    0.46
    ISER
    0.46
    では
    0.45
    ‌اند
    0.45
    Activations Density 0.003%

    No Known Activations