© 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. 10894
    Prev
    Next
    INDEX
    Explanations

    first and foremost

    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
    Př
    1.44
    På
    1.34
    ン
    1.34
    Além
    1.30
    (^^
    1.27
     మరియు
    1.21
    Пер
    1.21
    郤
    1.20
    ড়যন্ত্র
    1.20
    ن
    1.18
    POSITIVE LOGITS
    1.59
    ic
    1.56
     importantly
    1.55
    ت
    1.46
    м
    1.41
    withstanding
    1.38
     abide
    1.37
    ро
    1.35
    ри
    1.35
    ле
    1.30
    Activations Density 0.000%

    No Known Activations