© 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. 41-GEMMASCOPE-2-RES-65K
    7. 14380
    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_41_width_65k_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
     antaranya
    0.60
     Ide
    0.58
     Stony
    0.58
     )$
    0.57
     Sunni
    0.56
     Justin
    0.54
     Cavaliers
    0.54
     Stain
    0.54
     Chromatogr
    0.53
     paintbrush
    0.53
    POSITIVE LOGITS
    GetChar
    0.59
    \{\
    0.56
    凡
    0.53
    \|_{\
    0.52
    另一方面
    0.52
    Specification
    0.51
    窄
    0.50
    Directions
    0.49
    说明
    0.49
     направление
    0.49
    Activations Density 0.000%

    No Known Activations