© 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-262K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    how to section

    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_262k_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
    ंडन
    0.27
     श्रद्धालुओं
    0.27
     достой
    0.27
    ్వర
    0.25
    <unused266>
    0.25
     جائز
    0.25
    DanhMucSP
    0.24
    securityMarks
    0.24
    pinimg
    0.24
     kDa
    0.24
    POSITIVE LOGITS
     section
    0.30
     function
    0.28
    ↵
    0.27
     parameters
    0.26
     `
    0.25
     d
    0.24
     method
    0.24
    Path
    0.24
     functions
    0.24
     formulas
    0.24
    Activations Density 0.823%

    No Known Activations