© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84620
    Prev
    Next
    INDEX
    Explanations

    兵马俑, 権兵衛, 病んでる

    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_40_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
    opub
    0.43
    unus
    0.41
    孖
    0.39
    부분
    0.38
     theres
    0.38
     braided
    0.37
    澪
    0.37
     Woodland
    0.37
     Word
    0.37
    パナソニック
    0.37
    POSITIVE LOGITS
     병
    0.47
    كية
    0.42
    acher
    0.42
    兵
    0.41
    병
    0.40
    azon
    0.40
    病
    0.39
    হাস
    0.38
    乓
    0.38
     değişik
    0.38
    Activations Density 0.001%

    No Known Activations