© 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. 87292
    Prev
    Next
    INDEX
    Explanations

    law and finance phrases

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

    sentence terminators

    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
    時
    0.53
     to
    0.50
    {
    0.50
    次元
    0.49
     Fav
    0.48
    的
    0.48
    一
    0.47
     og
    0.47
     Syndicate
    0.46
     解説
    0.45
    POSITIVE LOGITS
     miesią
    0.52
    alnız
    0.51
     юк
    0.51
     сучас
    0.50
    ifadə
    0.50
    isinde
    0.50
    therapeutic
    0.50
    govor
    0.49
     عہد
    0.48
    iejęt
    0.48
    Activations Density 0.000%

    No Known Activations