© 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. 232554
    Prev
    Next
    INDEX
    Explanations

    modal verbs and follow-up actions

    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
    یا
    0.50
     možda
    0.49
    LE
    0.46
    λογ
    0.45
    เงิน
    0.45
    માં
    0.45
    ளு
    0.44
    న్‌
    0.44
    売り
    0.44
    𝘨
    0.43
    POSITIVE LOGITS
     orientations
    0.50
     scopes
    0.49
     contexts
    0.48
     দেবযানী
    0.46
     contextos
    0.46
     bouts
    0.46
    kits
    0.46
    wat
    0.44
     estimators
    0.44
     helpers
    0.43
    Activations Density 0.004%

    No Known Activations