© 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. 13034
    Prev
    Next
    INDEX
    Explanations

    S-Corp, League, metaphors, R&D, helps

    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
    ،
    0.48
    േഷ
    0.47
     전망
    0.47
     युवाओं
    0.46
    <unused374>
    0.44
     jeunes
    0.43
     і
    0.43
     voor
    0.43
     انٹر
    0.43
     είναι
    0.43
    POSITIVE LOGITS
    向
    0.42
    来
    0.42
     conversion
    0.40
     rectMode
    0.39
     特定
    0.39
    ch
    0.39
    igui
    0.39
     undercut
    0.38
    フ
    0.38
    同
    0.38
    Activations Density 0.006%

    No Known Activations