© 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. 114098
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    volume, minutes, type, passages, Meta

    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
     MOTOR
    0.54
    TEGER
    0.53
     मरने
    0.52
    INSON
    0.50
     lahan
    0.49
    忱
    0.47
     Manifesto
    0.46
     अलविदा
    0.46
     मजबूर
    0.46
    ৬
    0.46
    POSITIVE LOGITS
    o
    0.55
     simplifies
    0.52
     coi
    0.50
    fing
    0.49
    u
    0.48
    k
    0.48
     inhibiting
    0.47
     memorials
    0.46
    geries
    0.46
    e
    0.46
    Activations Density 0.001%

    No Known Activations