© 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. 223798
    Prev
    Next
    INDEX
    Explanations

    you currently address

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

    rewards and punishments

    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
    ủy
    0.49
     संदिग्ध
    0.48
    ｡
    0.47
     新品
    0.46
     युग
    0.46
     おすすめ
    0.46
    anut
    0.45
     ตัด
    0.45
     Каза
    0.45
     मोबाइल
    0.45
    POSITIVE LOGITS
     detta
    0.46
     de
    0.45
     und
    0.44
     Goldstein
    0.44
     coordinator
    0.43
    لق
    0.43
     intertw
    0.42
     interrupted
    0.42
    鬥
    0.41
     Coordinator
    0.41
    Activations Density 0.000%

    No Known Activations