© 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. 221
    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
    ে
    0.67
    i
    0.66
    ി
    0.64
    ς
    0.62
    e
    0.61
    ه
    0.58
    ી
    0.56
     etap
    0.56
    ों
    0.55
     enchanting
    0.54
    POSITIVE LOGITS
    '
    0.73
    תה
    0.61
     fornisce
    0.60
    .
    0.60
    ibatkan
    0.58
    いた
    0.58
    𝓉
    0.57
    ad
    0.56
    مسه
    0.55
    čne
    0.54
    Activations Density 0.448%

    No Known Activations