© 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. 96671
    Prev
    Next
    INDEX
    Explanations

    diagram after wiring

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

    code structure and functions

    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
    さんに
    0.48
    🏡
    0.46
     વરસાદ
    0.46
     कंट्री
    0.46
     पूछते
    0.45
     सहा
    0.45
    湇
    0.45
     इं
    0.44
    䐈
    0.44
    👔
    0.44
    POSITIVE LOGITS
     rapidity
    0.49
     castles
    0.48
     gallant
    0.47
     carefully
    0.46
     gameplay
    0.46
     knights
    0.45
     utterances
    0.45
     speeds
    0.43
     neither
    0.43
     antagonists
    0.43
    Activations Density 0.001%

    No Known Activations