© 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. 37598
    Prev
    Next
    INDEX
    Explanations

    sqlalchemy imports

    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
    ن
    1.79
     Direito
    1.58
    '.
    1.55
    र
    1.54
    artige
    1.53
    اء
    1.49
    ressing
    1.49
    а
    1.49
    iva
    1.47
    ami
    1.47
    POSITIVE LOGITS
    ्स
    2.22
    い
    2.03
    
    1.90
    ました
    1.88
     neoplasms
    1.87
     cryptocur
    1.85
    ╅
    1.83
    󰡔
    1.79
     ◆
    1.77
     twenties
    1.76
    Activations Density 0.001%

    No Known Activations