© 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. 10907
    Prev
    Next
    INDEX
    Explanations

    software names and 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
    لون
    0.48
    رز
    0.42
    ل
    0.41
    دت
    0.39
    中心
    0.38
    واكب
    0.38
    ্বর
    0.38
    ဦ
    0.38
    の為
    0.37
    عمل
    0.37
    POSITIVE LOGITS
     Affairs
    0.42
    .
    0.41
    
    0.40
    и
    0.40
     СА
    0.39
     Α
    0.39
     ଅ
    0.38
    Ass
    0.38
    Α
    0.38
    ließlich
    0.38
    Activations Density 0.070%

    No Known Activations