© 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. 43486
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
     ਹੀ
    1.71
    ında
    1.65
    ની
    1.54
     jeopard
    1.53
     permitió
    1.50
    ের
    1.45
    我们在
    1.45
    섦
    1.45
    此刻
    1.42
     nascetur
    1.42
    POSITIVE LOGITS
    ق
    2.25
    ר
    1.91
    ت
    1.73
    ى
    1.73
    ת
    1.70
    ف
    1.62
    ج
    1.59
    k
    1.56
    pt
    1.52
    ки
    1.52
    Activations Density 0.070%

    No Known Activations