© 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. 28018
    Prev
    Next
    INDEX
    Explanations

    defining or relating terms

    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
     sects
    0.46
     disgu
    0.44
     malice
    0.43
    锹
    0.42
    ^{-
    0.42
    న్నా
    0.42
     wickedness
    0.42
    줘
    0.42
    ಾರ್ಥ
    0.42
    Hid
    0.41
    POSITIVE LOGITS
     crucial
    0.52
    的关键
    0.46
    的重要
    0.44
    重要的
    0.42
    abhäng
    0.38
     مرتبط
    0.38
    につなが
    0.37
     Connected
    0.36
     متعلق
    0.36
     derived
    0.36
    Activations Density 0.041%

    No Known Activations