© 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. 2950
    Prev
    Next
    INDEX
    Explanations

    in schema grants

    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
     صل
    0.41
     deliverance
    0.40
     murderous
    0.39
     م
    0.37
     produksi
    0.36
     تناول
    0.36
     ح
    0.35
     ا
    0.35
     غ
    0.35
     ع
    0.35
    POSITIVE LOGITS
    index
    0.46
    索引
    0.46
    id
    0.44
    Index
    0.43
    map
    0.42
    和
    0.42
    字段
    0.41
    List
    0.41
    mapping
    0.41
    目录
    0.41
    Activations Density 0.977%

    No Known Activations