© 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. 90002
    Prev
    Next
    INDEX
    Explanations

    required or instead

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

    curly braces and delimiters

    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
    0.74
    S
    0.74
     S
    0.68
     international
    0.64
     is
    0.62
    -
    0.61
     D
    0.61
     a
    0.58
     host
    0.57
     in
    0.55
    POSITIVE LOGITS
     مجھے
    0.56
    marshalN
    0.55
    ্লাস
    0.55
     문제는
    0.54
     ビタミン
    0.54
    傆
    0.54
     sasane
    0.53
    ColorBit
    0.53
    <unused1881>
    0.53
    㥳
    0.53
    Activations Density 0.001%

    No Known Activations