© 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. 220579
    Prev
    Next
    INDEX
    Explanations

    of pictures

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

    question is

    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
     newbies
    0.49
     ໜອງ
    0.49
    iritual
    0.47
     เช่น
    0.45
     مناطق
    0.45
     ત્યારે
    0.45
    ?</
    0.44
     रीजन
    0.44
     явления
    0.44
     зависи
    0.44
    POSITIVE LOGITS
    用於
    0.51
     transceiver
    0.50
    人用
    0.48
     screwdriver
    0.47
     coaxial
    0.45
    女士
    0.45
    李
    0.45
    紹
    0.44
    鞋
    0.44
    吊
    0.43
    Activations Density 0.002%

    No Known Activations