© 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. 11321
    Prev
    Next
    INDEX
    Explanations

    as far as i know

    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
    ला
    1.02
    斯
    0.95
    ล
    0.94
     appartiennent
    0.94
    ра
    0.93
    ರನ್ನು
    0.92
     voisines
    0.89
     année
    0.89
    我们
    0.88
    𝒉
    0.88
    POSITIVE LOGITS
    یر
    0.90
    Extensions
    0.80
    ib
    0.79
    tı
    0.78
    önt
    0.75
     p
    0.74
     k
    0.73
    ava
    0.73
     ση
    0.72
    的风
    0.72
    Activations Density 0.000%

    No Known Activations