© 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. 125862
    Prev
    Next
    INDEX
    Explanations

    making text more conversational

    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
    W
    0.46
     Sample
    0.46
     ష
    0.46
    閇
    0.45
     Independent
    0.44
     Kal
    0.44
     Se
    0.43
     unabhäng
    0.43
     చాలా
    0.43
     Investigación
    0.43
    POSITIVE LOGITS
    getColumnIndex
    0.48
    ᒻ
    0.47
     gial
    0.47
     trouva
    0.46
     формы
    0.46
     excès
    0.45
    mmas
    0.45
     puisqu
    0.44
    مین
    0.44
    ⵕ
    0.44
    Activations Density 0.003%

    No Known Activations