© 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. 468
    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
     అన్న
    0.93
    ⴻ
    0.91
    ানুভূতি
    0.90
     américain
    0.89
    ⴼ
    0.88
     großer
    0.87
     +#+
    0.84
     ormai
    0.84
     longitudinale
    0.84
     offrire
    0.82
    POSITIVE LOGITS
    car
    0.86
    те
    0.84
    cat
    0.81
    পে
    0.80
    ต
    0.79
    วิ
    0.78
    טן
    0.77
    IG
    0.74
    ك
    0.73
    ant
    0.73
    Activations Density 0.000%

    No Known Activations