© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133188
    Prev
    Next
    INDEX
    Explanations

    pathways or conduits

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

    passage through or via

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ומ
    0.48
     ಮತ್ತು
    0.46
    處理
    0.46
    এবং
    0.45
     ਅਤੇ
    0.45
    照
    0.41
    クレジットカード
    0.41
    スティ
    0.41
    錄
    0.40
    榃
    0.40
    POSITIVE LOGITS
     tramite
    0.53
     via
    0.52
     vía
    0.46
     either
    0.45
     Outlet
    0.45
     Via
    0.44
     entweder
    0.41
     someplace
    0.41
     либо
    0.40
     SE
    0.40
    Activations Density 0.020%

    No Known Activations