© 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. 54236
    Prev
    Next
    INDEX
    Explanations

    management, shop, legally, passage, extensive

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

    containers, division, find

    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
    et
    0.56
    x
    0.54
    م
    0.53
    (
    0.51
    <0x0D>
    0.50
    arr
    0.50
    ق
    0.50
    o
    0.48
    نس
    0.48
    normal
    0.47
    POSITIVE LOGITS
     менедже
    0.52
     מב
    0.51
     catalyzes
    0.50
     издание
    0.49
     प्रतिरोध
    0.48
     индекс
    0.47
     সংকোচন
    0.46
     مقاوم
    0.46
     isomorphism
    0.46
     формата
    0.46
    Activations Density 0.000%

    No Known Activations