© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145418
    Prev
    Next
    INDEX
    Explanations

    persons

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    a
    1.69
    ال
    1.61
    t
    1.52
    b
    1.45
    d
    1.29
    the
    1.21
    ر
    1.21
    in
    1.20
    A
    1.20
    e
    1.19
    POSITIVE LOGITS
    ла
    1.15
    ৭
    0.96
    ларга
    0.94
    .
    0.88
    ריה
    0.86
    ﻧ
    0.83
    ﻟ
    0.82
    ﺭ
    0.81
    ৩
    0.80
    лан
    0.78
    Activations Density 0.000%

    No Known Activations