© 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-65K
    7. 16985
    Prev
    Next
    INDEX
    Explanations

    percentage rates

    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_65k_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
    璽
    0.47
    Õ
    0.46
    0
    0.45
     ۔
    0.43
    Ma
    0.42
    と言
    0.41
    _{\
    0.41
    0.41
     किसी
    0.41
    Let
    0.40
    POSITIVE LOGITS
     mirip
    0.43
    ена
    0.42
     prok
    0.41
     flavoring
    0.41
    ዣ
    0.41
     moisturizing
    0.39
     perjud
    0.39
     Carefully
    0.39
     జాగ్ర
    0.38
     тщательно
    0.38
    Activations Density 0.002%

    No Known Activations