© 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. 84711
    Prev
    Next
    INDEX
    Explanations

    Brussels sprouts

    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
     syscall
    0.44
     gto
    0.42
    JOHN
    0.41
    чили
    0.38
    लिप
    0.38
     savage
    0.37
    ⋙
    0.37
    modelLogin
    0.37
    墉
    0.37
     vacanam
    0.36
    POSITIVE LOGITS
    spers
    0.45
    Grouping
    0.41
    prevent
    0.40
    グループ
    0.40
    pian
    0.40
     предотвра
    0.40
     phát
    0.39
     ups
    0.39
     molte
    0.38
    aporan
    0.38
    Activations Density 0.001%

    No Known Activations