© 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. 115
    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
    。
    0.80
    Blob
    0.74
    ।
    0.73
    ،
    0.69
    。)
    0.64
    )。
    0.63
    )，
    0.63
     sourcing
    0.62
    uce
    0.62
     ngọt
    0.62
    POSITIVE LOGITS
     জি
    0.95
    朓
    0.87
     Poirot
    0.86
     Poincaré
    0.84
    ్ఞ
    0.84
     معلومات
    0.83
    勅
    0.83
    بة
    0.83
     rango
    0.83
     Sih
    0.82
    Activations Density 0.000%

    No Known Activations