© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8805
    Prev
    Next
    INDEX
    Explanations

    Structured lists and technical terms

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

    organizational scaffolding in expository or instructional text, especially phrases that introduce breakdowns, lists, sections, or step-by-step guides.

    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
    ujjati
    0.32
     названием
    0.30
     출력
    0.30
     BeautifulSoup
    0.29
    颜色
    0.28
    靥
    0.28
    类型
    0.27
     {@
    0.27
     occurrence
    0.27
    对象
    0.27
    POSITIVE LOGITS
    H
    0.40
    اي
    0.34
    P
    0.33
    AI
    0.33
    HER
    0.32
    G
    0.31
    T
    0.31
    Castle
    0.30
    AMS
    0.29
    HR
    0.29
    Activations Density 0.446%

    No Known Activations