© 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. 86987
    Prev
    Next
    INDEX
    Explanations

    your or you then too

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

    time indicators, status updates, and technical terms

    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
     অবস্থান
    0.45
    therefore
    0.41
    𒂵
    0.41
    MORDOR
    0.40
     daarom
    0.39
     سرزمین
    0.38
    summar
    0.38
    ोसिएशन
    0.38
     enmity
    0.38
    ශ්‍ය
    0.38
    POSITIVE LOGITS
    +
    0.56
    -
    0.50
    (
    0.49
    =
    0.46
    :
    0.45
    .
    0.45
     nonzero
    0.43
    ),
    0.43
     jumpsuit
    0.43
     थिए
    0.43
    Activations Density 0.003%

    No Known Activations