© 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. 253743
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ة
    0.55
    ing
    0.54
    据说
    0.44
    an
    0.42
     eukaryotic
    0.42
    quela
    0.41
    ä
    0.41
     ಮೇ
    0.40
    鳧
    0.40
    ad
    0.40
    POSITIVE LOGITS
     ремонта
    0.47
     достав
    0.47
     распоря
    0.47
    <unused975>
    0.46
    grids
    0.46
    Ports
    0.46
    <unused682>
    0.45
    <unused995>
    0.45
    <unused216>
    0.45
    <unused1983>
    0.45
    Activations Density 0.002%

    No Known Activations