© 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. 12-GEMMASCOPE-2-RES-16K
    7. 84
    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_12_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
    सामाजिक
    0.99
    का
    0.95
     esclusivamente
    0.94
    जैसे
    0.94
    हालांकि
    0.93
     defaul
    0.91
    с
    0.91
    その
    0.90
     esclus
    0.89
    ইংরে
    0.89
    POSITIVE LOGITS
     жидкости
    0.86
     ((
    0.83
     provoque
    0.82
     پیام
    0.81
     Batch
    0.80
    reacted
    0.77
     Ủy
    0.73
     వద్ద
    0.73
    ℉
    0.72
    io
    0.72
    Activations Density 0.000%

    No Known Activations