© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    division, modulo, indexing

    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
    ᆭ
    0.17
     permukaan
    0.16
    geqq
    0.16
    dicke
    0.16
     Elovl
    0.16
    疾患
    0.15
    ῴ
    0.15
    PosZ
    0.15
    謖
    0.15
     khuẩn
    0.15
    POSITIVE LOGITS
     %
    0.20
     [
    0.19
     in
    0.17
     a
    0.17
     -
    0.17
      
    0.17
     To
    0.17
     higher
    0.17
     Sim
    0.17
     *
    0.16
    Activations Density 0.106%

    No Known Activations