© 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. 174355
    Prev
    Next
    INDEX
    Explanations

    layering and integration

    np_acts-logits-general · gemini-2.5-flash-lite

    listing specific items and notes

    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
    Krishna
    0.51
    ;
    0.50
     Rajput
    0.50
    jee
    0.48
     Swami
    0.48
    4
    0.48
     khas
    0.48
    Rajasthan
    0.47
     Wallace
    0.47
     lakhs
    0.47
    POSITIVE LOGITS
     फलस्वरूप
    0.51
     બનાવે
    0.50
     注意
    0.50
     ঘটন
    0.49
     تساوي
    0.48
     非
    0.48
     आंतरिक
    0.47
     Größe
    0.47
     المسافه
    0.47
     सफलतापूर्वक
    0.47
    Activations Density 0.002%

    No Known Activations