© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48481
    Prev
    Next
    INDEX
    Explanations

    change over time

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     নিরাপদ
    0.54
     repel
    0.53
     রাইফ
    0.52
    ပိုင်း
    0.50
    し
    0.50
    ;|&
    0.49
    $，
    0.49
    Ꮯ
    0.49
    ﺹ
    0.49
    ত্যার
    0.49
    POSITIVE LOGITS
    .
    0.51
    0.49
     الع
    0.45
     س
    0.44
    ↵
    0.43
    ز
    0.41
    ft
    0.41
    Kurs
    0.41
    ++
    0.40
    Incoming
    0.39
    Activations Density 0.000%

    No Known Activations