© 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. 103599
    Prev
    Next
    INDEX
    Explanations

    for or raising or supporting

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

    ignore, excuse, reintroduce

    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
    Negative Logits
     CAPITAL
    0.44
    ಂದರೆ
    0.44
     langer
    0.43
    াভাবিক
    0.43
    ANG
    0.42
     panjang
    0.42
    EMPLOY
    0.41
    arod
    0.41
    ]]
    0.40
    orescent
    0.40
    POSITIVE LOGITS
    谍
    0.46
     Expedia
    0.46
     süreç
    0.43
     é
    0.43
     Lyft
    0.43
     ढा
    0.42
     সন্ধান
    0.42
    结算
    0.42
     Perk
    0.42
    ѧ
    0.42
    Activations Density 0.001%

    No Known Activations