© 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. 111047
    Prev
    Next
    INDEX
    Explanations

    about lithograph, volume, library

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

    childcare, software, cost, brake, music, units, Soviet

    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
     cure
    0.52
    ל
    0.47
     remplir
    0.47
     cohort
    0.46
     treasury
    0.46
    სი
    0.45
    aganda
    0.45
     miracle
    0.45
    дору
    0.44
     precinct
    0.44
    POSITIVE LOGITS
    [][
    0.49
     Kiểm
    0.46
     அப்போது
    0.45
    !;
    0.43
     Szer
    0.43
    [];
    0.43
    extends
    0.43
     khớp
    0.43
    ṗ
    0.43
     কার্যত
    0.42
    Activations Density 0.000%

    No Known Activations