© 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. 12716
    Prev
    Next
    INDEX
    Explanations

    identify claims or profiles

    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
     dalam
    0.49
     داخل
    0.42
     actuel
    0.41
     také
    0.41
     inom
    0.41
     ج
    0.40
     atual
    0.40
     ا
    0.39
     kom
    0.39
     ت
    0.39
    POSITIVE LOGITS
    各个
    0.49
     各
    0.45
    >=</
    0.41
    overline
    0.40
    কে
    0.40
    ("
    0.40
    ()
    0.40
    的所有
    0.39
    解析
    0.38
     每个
    0.38
    Activations Density 0.121%

    No Known Activations