© 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. 5824
    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
    чки
    0.79
    па
    0.78
    ⅽ
    0.77
    ди
    0.77
    ج
    0.77
    şt
    0.71
    сне
    0.70
    സിക
    0.70
    три
    0.70
    㳊
    0.69
    POSITIVE LOGITS
    laus
    0.84
     Meskipun
    0.82
     meskipun
    0.79
     n
    0.78
    reck
    0.76
     fech
    0.76
     игровой
    0.76
     Australians
    0.75
     atraves
    0.75
    flood
    0.75
    Activations Density 0.000%

    No Known Activations