© 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. 4026
    Prev
    Next
    INDEX
    Explanations

    list item

    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
     분포
    0.42
    mujer
    0.42
     pInBuffer
    0.42
     distribuição
    0.41
    ╋
    0.41
    벡터
    0.40
     кислоты
    0.40
    جموع
    0.40
     nCmdShow
    0.39
    тивних
    0.39
    POSITIVE LOGITS
     item
    1.60
     items
    1.53
    item
    1.39
     Item
    1.30
    items
    1.28
     Items
    1.23
    Item
    1.19
    アイテム
    1.13
    Items
    1.09
    项
    1.08
    Activations Density 0.008%

    No Known Activations