© 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. 16-GEMMASCOPE-2-RES-262K
    7. 29647
    Prev
    Next
    INDEX
    Explanations

    traces or vestiges

    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
    ра
    0.77
    ти
    0.75
    는
    0.61
    ',
    0.59
    ча
    0.56
    gled
    0.55
     Roos
    0.55
    必要な
    0.54
     Lettuce
    0.54
    не
    0.53
    POSITIVE LOGITS
     traces
    0.77
     vestiges
    0.75
    at
    0.69
    os
    0.65
    ا
    0.63
     ..."
    0.62
    ut
    0.61
     imposes
    0.61
    IC
    0.60
     reinforces
    0.60
    Activations Density 0.001%

    No Known Activations