© 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. 256315
    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
    omie
    0.54
    वास्तव
    0.52
     प्रश्न
    0.48
    enregist
    0.48
     egyes
    0.48
    ရင်း
    0.47
    슬
    0.47
    ීම
    0.47
    이에
    0.47
    ତ୍
    0.46
    POSITIVE LOGITS
     manipulator
    0.46
    চিতের
    0.46
     soups
    0.43
     tarp
    0.43
     vamp
    0.43
     nozzles
    0.42
     whey
    0.42
     shelf
    0.42
    зов
    0.41
     sapon
    0.41
    Activations Density 0.001%

    No Known Activations