© 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-16K
    7. 10213
    Prev
    Next
    INDEX
    Explanations

    hardware wallets, bus, vacuum

    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_16k_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
    s
    1.20
    whitelist
    1.09
    views
    0.93
    ignore
    0.90
    ar
    0.90
     legge
    0.90
    ים
    0.89
    teachers
    0.88
     cucina
    0.88
    when
    0.87
    POSITIVE LOGITS
    ﺤ
    0.89
     Тыва
    0.87
    ИТ
    0.86
    Etiam
    0.86
    부터
    0.83
    ୀ
    0.81
     Ters
    0.79
     nút
    0.78
    డ్
    0.78
    ITOR
    0.78
    Activations Density 0.001%

    No Known Activations