© 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. 41183
    Prev
    Next
    INDEX
    Explanations

    golf

    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
     写
    0.54
    劏
    0.52
     SimSun
    0.50
     రచ
    0.47
     ರಚ
    0.47
     писать
    0.46
    League
    0.46
    郅
    0.46
     Writing
    0.46
    Writing
    0.46
    POSITIVE LOGITS
     golf
    1.41
    Golf
    1.21
     Golf
    1.20
    golf
    1.16
     golfing
    1.16
     golfers
    1.15
     golfer
    1.10
    ゴルフ
    1.04
    🏌
    0.95
     ゴルフ
    0.95
    Activations Density 0.011%

    No Known Activations