© 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. 49117
    Prev
    Next
    INDEX
    Explanations

    any kind

    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
    cm
    0.47
     সিনেমা
    0.44
     হওয়
    0.43
    真的是
    0.42
    帀
    0.42
     कल्चर
    0.41
    瑤
    0.41
    лары
    0.41
    was
    0.40
     मामलों
    0.39
    POSITIVE LOGITS
     теку
    0.47
    ，
    0.46
     துவ
    0.44
      
    0.44
     вда
    0.42
     шан
    0.41
    。
    0.41
     <
    0.41
     제한
    0.41
    ،
    0.41
    Activations Density 0.000%

    No Known Activations