© 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. 224346
    Prev
    Next
    INDEX
    Explanations

    Authorized pickups

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

    protocol completion

    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
    雅
    0.54
    นัก
    0.54
    かず
    0.45
    প্রধান
    0.45
    кси
    0.44
    יית
    0.44
     Джа
    0.44
     силу
    0.44
    Ы
    0.44
    urazione
    0.43
    POSITIVE LOGITS
    ína
    0.50
     Innovations
    0.46
    otides
    0.46
     为了
    0.46
     Oles
    0.44
     stö
    0.44
     képes
    0.43
    alos
    0.43
    Linq
    0.43
     Agro
    0.43
    Activations Density 0.000%

    No Known Activations