© 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. 25637
    Prev
    Next
    INDEX
    Explanations

    money denominations

    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
     関数
    0.46
     상수
    0.44
    滑动
    0.44
     相
    0.43
    kontrol
    0.42
    ต่าง
    0.42
     квадрат
    0.42
     תי
    0.41
     BatchNorm
    0.41
    🔁
    0.41
    POSITIVE LOGITS
     penny
    0.57
     quarter
    0.55
     nickel
    0.48
     pennies
    0.47
     Quarter
    0.45
     half
    0.44
     Penny
    0.43
     possession
    0.43
     water
    0.43
     debt
    0.42
    Activations Density 0.048%

    No Known Activations