© 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. 10584
    Prev
    Next
    INDEX
    Explanations

    during specific contexts

    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
    ار
    2.16
    il
    2.13
    ā
    2.13
    re
    2.06
    ר
    2.05
    м
    2.02
    ರ
    1.98
    v
    1.94
    র
    1.94
    о
    1.92
    POSITIVE LOGITS
    د
    3.05
     وبعد
    3.00
    에는
    2.52
    이나
    2.45
    ى
    2.45
     וכ
    2.41
    ي
    2.39
    ពេល
    2.14
    ি
    2.09
     διάρκεια
    2.03
    Activations Density 0.030%

    No Known Activations