© 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. 11257
    Prev
    Next
    INDEX
    Explanations

    optical excitation, imagery, sensors, emission

    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
    ин
    1.66
    ל
    1.64
    וד
    1.57
    ค์
    1.57
    আ
    1.55
    І
    1.55
    ול
    1.55
    ী
    1.54
    ل
    1.53
    তি
    1.48
    POSITIVE LOGITS
    y
    2.42
    ין
    2.31
    특별시
    2.27
    eers
    2.25
    ‌లో
    2.17
    𝘻
    2.14
    ي
    2.13
    yah
    2.11
    며
    2.08
    ation
    2.02
    Activations Density 0.001%

    No Known Activations