© 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. 3842
    Prev
    Next
    INDEX
    Explanations

    superscripts or exponents

    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
    ال
    1.84
    นะคะ
    1.73
    ました
    1.65
    s
    1.63
    นะครับ
    1.61
    te
    1.50
    ної
    1.48
    sley
    1.48
    ى
    1.46
    in
    1.40
    POSITIVE LOGITS
    ہ
    2.02
     Při
    1.73
    Đây
    1.66
    ని
    1.64
     epitopes
    1.63
    Waar
    1.63
    তরাং
    1.63
     desember
    1.63
     rotacao
    1.61
    Hej
    1.59
    Activations Density 0.023%

    No Known Activations