© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4053
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ع
    1.09
     bilangan
    0.93
    рия
    0.91
    ح
    0.91
    리
    0.87
     étudier
    0.84
    ující
    0.81
     également
    0.80
     voire
    0.80
    进而
    0.80
    POSITIVE LOGITS
    дентификаторы
    0.98
    ль
    0.98
    あります
    0.96
    леты
    0.93
     trusty
    0.91
     Snoop
    0.88
    льники
    0.87
    те
    0.85
     pesky
    0.84
    ੇ
    0.83
    Activations Density 0.104%

    No Known Activations