© 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. 10644
    Prev
    Next
    INDEX
    Explanations

    metadata

    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
    י
    1.75
    ﺭ
    1.72
    ם
    1.68
    ו
    1.62
    ای
    1.60
    ă
    1.59
    킹
    1.56
    oon
    1.55
    盉
    1.55
    그래
    1.52
    POSITIVE LOGITS
    AR
    2.13
    og
    2.03
    AN
    2.03
    šie
    1.99
    ної
    1.83
     rendel
    1.80
    ører
    1.77
    IN
    1.75
     khoa
    1.75
    AS
    1.72
    Activations Density 0.020%

    No Known Activations