© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    goal completion punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    abstract, concept-heavy content words that convey themes, aesthetics, or high-level domains (e.g., experimentation, atmosphere, networks, future, authenticity, success) rather than function words.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ন্যার
    0.22
    ファイルを
    0.21
    ങ്ങളും
    0.21
    ="))
    0.20
     های
    0.20
    埸
    0.20
    édez
    0.20
    িগণ
    0.20
     ഇത
    0.19
     విధంగా
    0.19
    POSITIVE LOGITS
    。
    0.43
    ."
    0.32
    .
    0.31
    .”
    0.30
    ។
    0.30
    .)
    0.27
    ".
    0.27
    ።
    0.27
    .*
    0.26
    ).
    0.25
    Activations Density 3.816%

    No Known Activations