© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 198101
    Prev
    Next
    INDEX
    Explanations

    historical figures and classic models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ◄
    0.44
     különböző
    0.44
     कहानियां
    0.40
    stylers
    0.40
    基本的に
    0.39
    Depending
    0.39
     Racing
    0.39
    DataObject
    0.39
     یکی
    0.38
     मांसपेशियों
    0.38
    POSITIVE LOGITS
     Homo
    0.40
     fis
    0.39
     Ó
    0.39
     Sot
    0.39
     Incorpor
    0.38
     betta
    0.38
     usern
    0.38
    empor
    0.37
    issait
    0.37
     Stre
    0.36
    Activations Density 0.092%

    No Known Activations