© 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. 211747
    Prev
    Next
    INDEX
    Explanations

    handling small, note that, numbers as

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

    counting, forecasting, or categorizing

    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
    ↵
    0.43
     collect
    0.42
     teach
    0.42
    ืช
    0.41
     što
    0.41
     lui
    0.40
     làm
    0.40
    揭
    0.39
     float
    0.39
     делают
    0.39
    POSITIVE LOGITS
     भाषाओं
    0.53
    rzez
    0.51
     vattum
    0.51
    ಟಿ
    0.50
    ለያዩ
    0.49
    новні
    0.49
     архівної
    0.49
    listener
    0.49
    tx
    0.48
    modulation
    0.46
    Activations Density 0.000%

    No Known Activations