© 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. 40826
    Prev
    Next
    INDEX
    Explanations

    predecessors, founders, pioneers

    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
    ları
    1.49
    EST
    1.48
    岖
    1.48
    ant
    1.41
    ধন
    1.38
    ro
    1.37
    끔
    1.37
    ته
    1.30
     discolor
    1.30
    ﺱ
    1.29
    POSITIVE LOGITS
    ীর
    2.02
    erweise
    1.95
    Пре
    1.78
    اد
    1.68
    ingly
    1.66
    Aunque
    1.62
    Cómo
    1.59
    Tras
    1.59
    Когда
    1.59
    Witam
    1.58
    Activations Density 0.000%

    No Known Activations