© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259485
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     យើង
    0.56
    尣
    0.55
     ყ
    0.55
     வான
    0.53
    𝙙
    0.52
     लिखें
    0.52
     السابق
    0.51
     கிழக்கு
    0.50
     காட்டு
    0.50
    மையான
    0.50
    POSITIVE LOGITS
     hydrocarbons
    0.52
    O
    0.50
     material
    0.50
    (
    0.49
    otoxicity
    0.49
    in
    0.48
     fund
    0.47
     polymers
    0.46
     diameters
    0.46
     proteínas
    0.46
    Activations Density 0.001%

    No Known Activations