© 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. 35791
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming terms

    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
    ه‌های
    0.87
    respuesta
    0.82
    ólico
    0.79
    ه‌ای
    0.77
    आर
    0.77
    枞
    0.76
    stituto
    0.76
    های
    0.75
    сць
    0.75
    秇
    0.74
    POSITIVE LOGITS
    itu
    0.86
    0
    0.80
    il
    0.79
     Organization
    0.77
    ila
    0.75
    as
    0.73
    ov
    0.73
    ING
    0.72
    ak
    0.71
    itia
    0.71
    Activations Density 0.000%

    No Known Activations