© 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. 408
    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
    2
    0.65
    8
    0.65
    во
    0.64
    з
    0.64
    ed
    0.63
    5
    0.63
    4
    0.62
    ت
    0.61
    та
    0.61
    7
    0.61
    POSITIVE LOGITS
    s
    0.64
    fasterxml
    0.56
     पीरियड
    0.54
     umana
    0.54
    墅
    0.54
     consequent
    0.52
    要去
    0.52
    sau
    0.52
    ใน
    0.51
    要把
    0.50
    Activations Density 5.659%

    No Known Activations