© 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. 1219
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, and counts

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

    quantities and counts

    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
     veoma
    0.19
     wobei
    0.19
     leptonic
    0.18
     għ
    0.18
     ¹
    0.18
     fyrir
    0.18
     WHICH
    0.17
     了
    0.17
    ¹.
    0.17
     respectively
    0.17
    POSITIVE LOGITS
     हजार
    0.23
    数百
    0.22
     million
    0.21
     مليون
    0.20
     thousand
    0.20
     десятки
    0.20
     dozen
    0.19
     cientos
    0.19
     હજાર
    0.19
     हजारों
    0.19
    Activations Density 0.565%

    No Known Activations