© 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. 11412
    Prev
    Next
    INDEX
    Explanations

    no particular

    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
    ور
    2.81
    های
    2.77
    س
    2.64
    ти
    2.63
    ل
    2.44
    ق
    2.28
    ри
    2.22
    م
    2.13
    ер
    2.09
    া
    1.98
    POSITIVE LOGITS
    elfde
    1.84
    ্শন
    1.73
    স
    1.68
    ಲ್ಲಿ
    1.67
    ード
    1.66
    1.66
    IZATION
    1.64
    la
    1.63
    瘩
    1.63
    izes
    1.60
    Activations Density 0.024%

    No Known Activations