© 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. 10747
    Prev
    Next
    INDEX
    Explanations

    fiber

    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
    ري
    1.94
    ร
    1.80
    ре
    1.70
    स
    1.63
    لا
    1.60
    ز
    1.60
    Escolhido
    1.58
    mannschaft
    1.57
    ล
    1.56
    летие
    1.54
    POSITIVE LOGITS
    and
    2.16
    ka
    1.77
     energized
    1.69
    িক
    1.65
    ong
    1.64
     inconclusive
    1.62
     fiber
    1.57
     lượng
    1.57
     punctured
    1.56
    th
    1.55
    Activations Density 0.013%

    No Known Activations