© 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. 228321
    Prev
    Next
    INDEX
    Explanations

    dates and events

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     segera
    0.49
     aristocratic
    0.49
    ރ
    0.47
     denomination
    0.46
     Agora
    0.46
    نی
    0.45
     personas
    0.45
     musul
    0.45
     materialistic
    0.45
     exports
    0.44
    POSITIVE LOGITS
     результа
    0.51
     Avoiding
    0.50
    Avoiding
    0.48
     আঁচ
    0.47
    絨
    0.47
     найкра
    0.46
     удержи
    0.45
     Результа
    0.44
    ছুর
    0.44
     каждой
    0.44
    Activations Density 0.001%

    No Known Activations