© 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. 138887
    Prev
    Next
    INDEX
    Explanations

    replacing informal words

    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
     catalysis
    0.52
     قیمت
    0.46
    藺
    0.45
     cohesion
    0.45
    はじめ
    0.44
     使い
    0.44
     эффективности
    0.44
     казино
    0.43
     ژ
    0.43
     ደ
    0.43
    POSITIVE LOGITS
    deload
    0.52
     fiume
    0.49
    었습니다
    0.47
     thăm
    0.45
    ব
    0.44
     border
    0.43
    ?,
    0.43
    DROP
    0.43
    border
    0.43
    在
    0.42
    Activations Density 0.003%

    No Known Activations