© 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. 172026
    Prev
    Next
    INDEX
    Explanations

    or cause would can number meets

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

    involving cycles, not necessarily security

    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
     પ્રસ
    0.50
    愤
    0.45
    招待
    0.45
    棲
    0.43
    тков
    0.43
     Invited
    0.43
    women
    0.42
    其他人
    0.42
    Spatial
    0.42
    獻
    0.42
    POSITIVE LOGITS
     daunting
    0.48
     contraceptive
    0.48
     sculpting
    0.47
     alopecia
    0.47
     concealer
    0.47
     castration
    0.46
     unrelenting
    0.46
     באמצעות
    0.46
     logarithmic
    0.46
     parabolic
    0.46
    Activations Density 0.000%

    No Known Activations