© 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. 114051
    Prev
    Next
    INDEX
    Explanations

    tapas tour

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

    mathematical operations

    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
    ن
    0.63
     stalemate
    0.51
     closer
    0.50
     harsh
    0.50
     expiry
    0.49
     rematch
    0.48
     rear
    0.48
     general
    0.47
    و
    0.47
     redistribution
    0.46
    POSITIVE LOGITS
    anlage
    0.52
    kl
    0.50
     ピン
    0.50
     ໜ
    0.48
    ToShow
    0.48
    raisal
    0.48
     成分
    0.48
     അറിയ
    0.48
     プリント
    0.48
    agement
    0.46
    Activations Density 0.000%

    No Known Activations