© 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. 16420
    Prev
    Next
    INDEX
    Explanations

    flutter code examples

    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
     Bani
    0.39
    遗产
    0.38
    ItemLayout
    0.37
    냠
    0.37
    opolymer
    0.36
    ApiController
    0.36
     Widgets
    0.36
     बरेली
    0.35
    跛
    0.35
    ėj
    0.35
    POSITIVE LOGITS
     equiv
    0.43
    nsk
    0.42
     pula
    0.39
     équ
    0.39
    uuid
    0.38
    yaml
    0.37
    equ
    0.37
    tencent
    0.36
    schw
    0.36
    sdl
    0.36
    Activations Density 0.003%

    No Known Activations