© 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-16K
    7. 14723
    Prev
    Next
    INDEX
    Explanations

    XML layout binding

    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_16k_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
    ায়
    1.26
    ায়
    1.16
     That
    1.16
    ați
    1.14
    ation
    1.12
    imble
    1.11
    л
    1.11
    𝘴
    1.11
    ات
    1.09
    و
    1.08
    POSITIVE LOGITS
    ură
    1.08
     বৈঠকে
    1.03
    Ễ
    1.02
     aussitôt
    0.99
     voire
    0.97
    Giải
    0.95
    
    0.95
     ແມ່ນ
    0.95
     Sánchez
    0.94
    结构
    0.93
    Activations Density 0.002%

    No Known Activations