© 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. 107
    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
    该
    0.55
    此
    0.48
     চাইলে
    0.47
    salir
    0.45
    ዶ
    0.45
    siniz
    0.44
    ್ಯ
    0.42
    剧情
    0.42
    जो
    0.41
    specific
    0.41
    POSITIVE LOGITS
     extraordinaire
    0.54
     thrived
    0.52
     waged
    0.51
     dreamed
    0.49
     costruito
    0.48
     meravigli
    0.48
     thrives
    0.47
    ،
    0.46
     fuelled
    0.46
     naciones
    0.46
    Activations Density 0.000%

    No Known Activations