© 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. 4811
    Prev
    Next
    INDEX
    Explanations

    help to or me

    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
    ی
    1.10
     impuestos
    1.05
    ari
    1.00
    ،
    0.96
    s
    0.96
    {//
    0.93
     are
    0.90
    )،
    0.87
    ння
    0.85
    е
    0.84
    POSITIVE LOGITS
    n
    1.37
    ن
    1.20
     to
    1.20
    ン
    1.20
    ת
    1.20
    تي
    1.15
    ية
    1.14
    น
    1.14
    ing
    1.12
    то
    1.08
    Activations Density 0.109%

    No Known Activations