© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 42774
    Prev
    Next
    INDEX
    Explanations

    compulsions or byproducts

    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
    it
    1.66
    ่
    1.66
    ال
    1.54
    ৭
    1.51
    barui
    1.39
    ৮
    1.36
    ен
    1.35
     Еще
    1.35
    ist
    1.34
     И
    1.34
    POSITIVE LOGITS
    '
    1.34
     Lest
    1.33
     Ballroom
    1.30
     Receipts
    1.28
    нков
    1.27
    <0x80>
    1.27
    ไม่ใช่
    1.24
    Nasdaq
    1.21
    诩
    1.17
    ที่เป็น
    1.16
    Activations Density 0.001%

    No Known Activations