© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 1777
    Prev
    Next
    INDEX
    Explanations

    BF16, Focused Attention, microvolts

    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
     Staphylococcus
    0.22
     Jako
    0.22
     totiž
    0.22
     더욱
    0.21
     엄마
    0.21
    获取
    0.21
     అధికారు
    0.21
    💢
    0.21
    棂
    0.21
     집중
    0.21
    POSITIVE LOGITS
    _
    0.23
    ON
    0.22
    е
    0.22
    п
    0.22
     depending
    0.22
     ឬ
    0.21
    с
    0.21
    cse
    0.21
    нар
    0.21
    вЂ
    0.21
    Activations Density 1.176%

    No Known Activations