© 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. 55849
    Prev
    Next
    INDEX
    Explanations

    used for X

    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
    Not in Any Lists

    No Comments

    Negative Logits
    रखाव
    0.48
    ,..
    0.44
    ದಾರ
    0.43
    朝着
    0.42
    +","+
    0.42
    РА
    0.42
    XA
    0.42
    ..");
    0.41
     చేసుకోవ
    0.41
     Immigration
    0.41
    POSITIVE LOGITS
     coloring
    0.45
    様
    0.44
     reconnaître
    0.43
    coloring
    0.43
    嬢
    0.43
     vốn
    0.43
     défini
    0.43
     giá
    0.42
    日は
    0.42
    锁
    0.42
    Activations Density 0.002%

    No Known Activations