© 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. 80836
    Prev
    Next
    INDEX
    Explanations

    places and regions

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

    Arch Linux, tracked vehicles

    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
    ва
    0.61
    判定
    0.56
    喈
    0.56
    т
    0.52
    ти
    0.52
    ф
    0.52
    okhttp
    0.51
     лока
    0.51
    ệng
    0.50
    λ
    0.50
    POSITIVE LOGITS
     Nordic
    0.61
     Nord
    0.59
     Scandin
    0.58
     northern
    0.58
     nordic
    0.57
     nord
    0.57
     Scandinavian
    0.55
     Slavic
    0.55
     Kanada
    0.55
     Seite
    0.53
    Activations Density 0.513%

    No Known Activations