© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7708
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ק
    0.69
    اگر
    0.68
    िक
    0.64
    آن
    0.61
     phẳng
    0.57
     lắng
    0.55
    לא
    0.55
    賭
    0.55
     solemnly
    0.54
     กี่
    0.54
    POSITIVE LOGITS
     étages
    0.69
     gigantes
    0.68
     aeronaut
    0.67
     agrícola
    0.67
     ముఖ్య
    0.66
     necesitaba
    0.66
     lingü
    0.65
    一代
    0.64
     generando
    0.64
     aviation
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.