© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144634
    Prev
    Next
    INDEX
    Explanations

    wise mouse

    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/layer_16_width_262k_l0_medium
    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
    s
    0.80
    soci
    0.55
    subject
    0.54
    socket
    0.49
    sı
    0.49
    soc
    0.48
    sop
    0.48
    socks
    0.47
    symmetry
    0.46
    헙
    0.46
    POSITIVE LOGITS
     previewBuilder
    0.52
     তোমার
    0.51
     তুমি
    0.50
     tè
    0.49
     particulates
    0.49
     നീ
    0.47
     Laksh
    0.47
     interceptions
    0.47
     المصفوفه
    0.47
     atha
    0.46
    Activations Density 0.001%

    No Known Activations