© 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. 7655
    Prev
    Next
    INDEX
    Explanations

    stage presence or setting

    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
    ab
    2.02
    ar
    1.93
    श
    1.90
    ou
    1.87
    ru
    1.71
    el
    1.70
    arjo
    1.70
    ps
    1.69
     кстати
    1.69
    rtel
    1.69
    POSITIVE LOGITS
    tır
    2.05
    ка
    2.02
    ни
    1.99
     améli
    1.98
    ารย์
    1.96
    нага
    1.95
     nhàng
    1.94
    дій
    1.90
    于是
    1.86
    ج
    1.84
    Activations Density 0.012%

    No Known Activations