© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 37
    Prev
    Next
    INDEX
    Explanations

    core structural elements

    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_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
    발
    0.33
     stubbornly
    0.33
     sog
    0.32
    PRI
    0.32
     phát
    0.31
     관심을
    0.31
    Criminal
    0.31
    pronounced
    0.28
    発
    0.28
    েলি
    0.28
    POSITIVE LOGITS
    さまざ
    0.34
     растение
    0.33
     دوسری
    0.33
    आयु
    0.33
    塭
    0.32
    筮
    0.31
    мое
    0.31
    ेड
    0.31
     растения
    0.31
    statistik
    0.31
    Activations Density 0.003%

    No Known Activations