© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    manual

    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
    م
    1.90
    ಾ
    1.87
    p
    1.83
    म
    1.77
                    
    1.72
    iyoruz
    1.72
    m
    1.70
    ാ
    1.70
    ind
    1.69
                
    1.66
    POSITIVE LOGITS
    smanship
    1.91
    τητα
    1.86
     말미암
    1.83
    শক
    1.77
     deftly
    1.76
    ਢ
    1.75
     cherish
    1.73
     ascribe
    1.73
     ardu
    1.70
    Ту
    1.70
    Activations Density 0.019%

    No Known Activations