© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52711
    Prev
    Next
    INDEX
    Explanations

    LaTeX environments and commands

    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
    Negative Logits
     LANE
    0.47
    ാര
    0.39
     Lane
    0.39
    Lane
    0.39
     arrays
    0.38
     reverses
    0.38
     ব্রণ
    0.38
    成员
    0.38
     पांडेय
    0.38
    _
    0.37
    POSITIVE LOGITS
     жить
    0.48
     zeal
    0.47
    кового
    0.44
     surpl
    0.42
     zealous
    0.42
    funk
    0.41
     beeinfl
    0.41
     дело
    0.41
     believed
    0.41
    uillez
    0.41
    Activations Density 0.002%

    No Known Activations