© 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. 12856
    Prev
    Next
    INDEX
    Explanations

    java code context

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     catheter
    0.79
     Pasha
    0.78
     bladder
    0.74
     cannula
    0.70
     WebSocket
    0.70
     #-
    0.69
     watched
    0.68
     dai
    0.68
     PZ
    0.68
     kati
    0.68
    POSITIVE LOGITS
    sports
    0.78
    Fundamentals
    0.75
    sons
    0.75
    보
    0.73
    take
    0.73
    transactions
    0.73
    tb
    0.72
    themem
    0.72
    냔
    0.71
    proportion
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.