© 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. 92410
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    result of

    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
     지정
    0.54
     belir
    0.54
     kontek
    0.53
     stanje
    0.50
     शैली
    0.49
     čini
    0.48
    ěz
    0.48
    .*/
    0.46
     определяет
    0.46
    iranje
    0.46
    POSITIVE LOGITS
    רו
    0.59
    رو
    0.54
    γά
    0.52
    рок
    0.51
    тур
    0.49
    ться
    0.49
    נו
    0.49
    צ
    0.48
    افت
    0.48
    瞼
    0.47
    Activations Density 0.000%

    No Known Activations