© 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. 362
    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
     rectangle
    0.77
     aree
    0.74
     Consultado
    0.62
    ો
    0.62
     sculptural
    0.61
    ד
    0.61
     liberalization
    0.59
     recuperación
    0.59
    нің
    0.59
     中
    0.59
    POSITIVE LOGITS
    mitting
    0.73
    rs
    0.72
    as
    0.71
    ers
    0.69
    いた
    0.69
    tene
    0.68
    ens
    0.68
    watches
    0.67
    to
    0.67
    ttes
    0.67
    Activations Density 3.469%

    No Known Activations