© 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. 90838
    Prev
    Next
    INDEX
    Explanations

    words preceding punctuation or conjunctions

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

    before, time, finally, attempting

    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
    ເວ
    0.52
    ブラ
    0.48
    機能を
    0.47
    裄
    0.47
     शुरू
    0.46
     kpc
    0.46
     پیشنه
    0.46
     साल
    0.46
     dietitian
    0.45
     கடந்த
    0.45
    POSITIVE LOGITS
    َم
    0.50
     an
    0.49
     Arrang
    0.49
     Provided
    0.48
    qvist
    0.48
     By
    0.47
     Doesn
    0.45
    usky
    0.45
    ail
    0.44
    awiają
    0.43
    Activations Density 0.002%

    No Known Activations