© 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. 315
    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
    יים
    0.58
     raspberry
    0.57
    y
    0.57
     tumble
    0.55
    eous
    0.55
     ikat
    0.55
     masterpiece
    0.54
     crux
    0.54
     Inspection
    0.53
     glaze
    0.52
    POSITIVE LOGITS
    们的
    0.72
    ’
    0.69
    innen
    0.63
    𝑖
    0.61
    间的
    0.61
    ’
    0.60
    们
    0.60
    👧
    0.59
    곁
    0.58
    inthe
    0.58
    Activations Density 6.280%

    No Known Activations