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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71086
    Prev
    Next
    INDEX
    Explanations

    field of, flags modify, wide range

    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
     tục
    0.52
     pensato
    0.50
    ブログ
    0.48
     takip
    0.47
     larva
    0.45
    гъл
    0.44
    單位
    0.43
    ޞ
    0.43
    getAvg
    0.43
     الطلبه
    0.43
    POSITIVE LOGITS
     Scottish
    0.47
     Northern
    0.44
    oules
    0.43
     Marsden
    0.42
    om
    0.42
    oside
    0.42
    odis
    0.41
     countries
    0.41
    也都
    0.41
     Maritime
    0.40
    Activations Density 0.000%

    No Known Activations