© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117885
    Prev
    Next
    INDEX
    Explanations

    dewatering screw

    np_acts-logits-general · gemini-2.5-flash-lite

    peak season, sense of, being understands, SOV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ಶ
    0.45
     conceivably
    0.45
    ʧ
    0.44
     መጠን
    0.43
     لینا
    0.43
     میل
    0.43
     λ
    0.42
     likelihood
    0.41
    assignmentItems
    0.41
     approximation
    0.41
    POSITIVE LOGITS
    imate
    0.53
    access
    0.51
    webpack
    0.49
    This
    0.48
    ui
    0.48
    小学
    0.48
    બ
    0.47
     Аб
    0.47
    Đây
    0.47
    inate
    0.46
    Activations Density 0.001%

    No Known Activations