© 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. 200522
    Prev
    Next
    INDEX
    Explanations

    national sporting

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

    Extended Essay

    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
     коллеги
    0.55
     ទ
    0.55
     Tengo
    0.53
     actualizado
    0.52
     Pesh
    0.49
     розы
    0.49
     actualizada
    0.48
     отделения
    0.48
     Thay
    0.48
     ابھی
    0.48
    POSITIVE LOGITS
    0
    0.50
    侧
    0.50
    club
    0.49
    Club
    0.49
    other
    0.48
    multiplier
    0.47
    compensation
    0.46
    post
    0.46
    Compensation
    0.46
    Ref
    0.46
    Activations Density 0.000%

    No Known Activations