© 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. 142494
    Prev
    Next
    INDEX
    Explanations

    when this

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

    building system descriptions

    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
     oorlog
    0.54
     guerras
    0.50
    埸
    0.50
    那边
    0.50
    㶱
    0.49
     берегу
    0.49
     وہاں
    0.48
    场
    0.46
     môn
    0.46
    觀眾
    0.46
    POSITIVE LOGITS
    prevent
    0.60
    ul
    0.58
    ut
    0.58
    inter
    0.57
    kom
    0.57
     proinflammatory
    0.57
    inflammatory
    0.55
    combined
    0.55
    ur
    0.55
    ergic
    0.55
    Activations Density 0.000%

    No Known Activations