© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191549
    Prev
    Next
    INDEX
    Explanations

    things are

    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_40_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
    iformis
    0.43
    Corners
    0.41
     ホーム
    0.41
    cInfo
    0.40
    गर
    0.38
    Mam
    0.38
    畯
    0.38
    inded
    0.37
     تاکہ
    0.37
    imester
    0.36
    POSITIVE LOGITS
    ुद्ध
    0.38
    sdx
    0.36
     થય
    0.35
     قابل
    0.35
    قابل
    0.35
    陡
    0.34
    öld
    0.34
     množství
    0.34
     solidity
    0.34
    lock
    0.33
    Activations Density 0.000%

    No Known Activations