© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3427
    Prev
    Next
    INDEX
    Explanations

    lists of numberscode snippetsmathematical conceptsspecific events/dates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    in
    0.95
    ו
    0.88
    ف
    0.88
    re
    0.83
    你
    0.80
    م
    0.79
    ↵
    0.78
    ే
    0.71
    k
    0.70
    ла
    0.70
    POSITIVE LOGITS
    1.60
     a
    0.97
    3
    0.80
    이다
    0.78
    اي
    0.77
    0
    0.77
     by
    0.75
    ﻦ
    0.73
     at
    0.71
     {
    0.71
    Activations Density 0.869%

    No Known Activations