© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8474
    Prev
    Next
    INDEX
    Explanations

    multilingual conjunctions and prepositions

    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
    s
    0.25
    修建
    0.23
     trusty
    0.23
    S
    0.21
    amily
    0.21
    家用
    0.20
    と一緒に
    0.19
    rile
    0.19
    ব্রিটিশ
    0.19
     neuest
    0.19
    POSITIVE LOGITS
     của
    0.39
     terhadap
    0.35
    และการ
    0.33
     ও
    0.33
     மற்றும்
    0.32
    ของการ
    0.31
     व
    0.30
     및
    0.29
     của
    0.29
     of
    0.29
    Activations Density 1.425%

    No Known Activations