© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10277
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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
    ра
    2.59
    ä
    2.02
    ре
    1.95
    ला
    1.95
    с
    1.91
    е
    1.80
    к
    1.77
    ă
    1.77
    ण
    1.76
    и
    1.71
    POSITIVE LOGITS
    gers
    1.82
    speople
    1.71
     CBN
    1.64
    tob
    1.63
    دة
    1.61
     tost
    1.61
    ことができる
    1.60
    ॅमिली
    1.58
     불구하고
    1.57
    gings
    1.56
    Activations Density 0.007%

    No Known Activations