© 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. 129080
    Prev
    Next
    INDEX
    Explanations

    information Act

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

    URL Ukraine PM sleep

    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
    ﺴ
    0.54
    創造
    0.49
    nade
    0.47
    strukt
    0.47
    rinde
    0.47
    ﺠ
    0.47
     ভারী
    0.46
     δημιουργ
    0.46
    <unused1>
    0.46
     कमाई
    0.46
    POSITIVE LOGITS
     watercolour
    0.46
     consid
    0.44
    {
    0.43
     afternoons
    0.43
     what
    0.42
     Xiaomi
    0.41
     gamepad
    0.41
     weatherproof
    0.41
     []
    0.40
     footpath
    0.40
    Activations Density 0.000%

    No Known Activations