© 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. 41961
    Prev
    Next
    INDEX
    Explanations

    most worth imitating

    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
    รวม
    1.44
    รับ
    1.40
    ร้าน
    1.36
    راہیم
    1.35
     ผ้า
    1.33
    یہ
    1.32
     る
    1.32
    รุ่น
    1.31
     Без
    1.30
     Delight
    1.30
    POSITIVE LOGITS
    ج
    1.51
    I
    1.35
    R
    1.27
    K
    1.20
    G
    1.16
    度和
    1.16
    を迎
    1.16
    ời
    1.15
    ículos
    1.14
    Node
    1.13
    Activations Density 0.000%

    No Known Activations