© 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-65K
    7. 20304
    Prev
    Next
    INDEX
    Explanations

    Continuing Education (CE)orFeatures

    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_65k_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
    nesi
    0.40
     regenerative
    0.39
     Prentice
    0.38
     spontaneous
    0.38
    شفى
    0.38
    礼
    0.38
     iterative
    0.37
    rana
    0.37
    m
    0.37
     ocurren
    0.36
    POSITIVE LOGITS
    Ԁ
    0.51
    ㄜ
    0.46
    ⅽ
    0.46
     Архі
    0.46
     argues
    0.45
     disagrees
    0.45
    </blockquote>
    0.44
    ҫ
    0.44
    дування
    0.43
     ЗА
    0.41
    Activations Density 0.014%

    No Known Activations