© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3257
    Prev
    Next
    INDEX
    Explanations

    participate in

    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
    ມີ
    1.70
    เป็น
    1.70
    มีการ
    1.60
    。
    1.60
    aneous
    1.57
    )$
    1.54
    に含ま
    1.52
    জনক
    1.47
    ，
    1.46
    );
    1.45
    POSITIVE LOGITS
    ە
    2.14
    ون
    2.13
    er
    2.06
    ar
    1.92
    ib
    1.89
    it
    1.85
    ار
    1.84
    ر
    1.84
    a
    1.77
    ট
    1.77
    Activations Density 0.015%

    No Known Activations