© 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. 108395
    Prev
    Next
    INDEX
    Explanations

    appendicitis or appendectomy

    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
    фа
    0.45
    Extensions
    0.44
    🐞
    0.44
    invalid
    0.43
     controllability
    0.41
    ні
    0.41
    Circles
    0.41
    Три
    0.40
    winkel
    0.40
     상세보기
    0.40
    POSITIVE LOGITS
    UME
    0.48
    ुल
    0.46
     궁
    0.44
     OPEC
    0.44
     ump
    0.43
     Moran
    0.42
     Hunters
    0.42
     police
    0.42
     campgrounds
    0.42
     KAY
    0.41
    Activations Density 0.004%

    No Known Activations