© 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. 17506
    Prev
    Next
    INDEX
    Explanations

    fever and milk

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

    structured, formal task–solution formatting—especially JSON/code blocks and step-by-step mathematical or algorithmic answers

    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_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
     эл
    0.48
    霭
    0.45
    旣
    0.44
     କ
    0.44
    ㄉ
    0.43
    xCoordinate
    0.43
    
    0.42
    梱包
    0.42
    elve
    0.41
    bmp
    0.41
    POSITIVE LOGITS
     protégé
    0.47
     doves
    0.44
    ிகள்
    0.43
     looser
    0.42
     Bored
    0.41
     birds
    0.41
     marriage
    0.41
     cache
    0.41
     combina
    0.41
     protege
    0.41
    Activations Density 3.645%

    No Known Activations