© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71453
    Prev
    Next
    INDEX
    Explanations

    may, capable, should, allows, when

    np_acts-logits-general · gemini-2.5-flash-lite

    part of what it represents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mania
    0.51
     নিত্য
    0.47
    ሸ
    0.45
    selling
    0.45
    ٽ
    0.45
    uire
    0.44
     توا
    0.43
    تح
    0.43
    planning
    0.41
    াইয়৷
    0.41
    POSITIVE LOGITS
    或其他
    0.50
     unborn
    0.49
                  
    0.48
     oder
    0.47
    _,
    0.46
     write
    0.45
     возможных
    0.45
    ξ
    0.45
     possibile
    0.44
    寫
    0.44
    Activations Density 0.001%

    No Known Activations