© 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. 16943
    Prev
    Next
    INDEX
    Explanations

    code structuring and closing symbols

    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
    CString
    0.38
    يس
    0.37
     interle
    0.37
    Z
    0.36
    glyph
    0.36
    ᅳ
    0.35
    rtle
    0.35
    Zaw
    0.34
    horas
    0.34
     ro
    0.34
    POSITIVE LOGITS
    🏡
    0.46
    シンプルな
    0.41
    आईपी
    0.39
    ल्लिंग
    0.38
    と思い
    0.38
    🤐
    0.38
    🌎
    0.38
    🏠
    0.38
    鳝
    0.37
    ForThe
    0.37
    Activations Density 0.004%

    No Known Activations