© 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. 822
    Prev
    Next
    INDEX
    Explanations

    calculate the sum, decimated the grid, realistic eyes

    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
    Кла
    0.54
    يدك
    0.52
    墾
    0.51
    حو
    0.51
    癣
    0.50
    ليك
    0.50
    дится
    0.50
    年モデル
    0.49
    يدي
    0.49
    的关键
    0.49
    POSITIVE LOGITS
     S
    0.54
    t
    0.52
    n
    0.50
     (
    0.50
    ill
    0.49
    sub
    0.48
     U
    0.48
     I
    0.48
    ta
    0.48
    r
    0.48
    Activations Density 0.000%

    No Known Activations