© 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. 138784
    Prev
    Next
    INDEX
    Explanations

    terms, child, life, elements

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

    context setters

    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
    ヴ
    0.45
     trái
    0.41
    seh
    0.40
     bind
    0.40
     connect
    0.39
     creative
    0.39
     deepen
    0.39
     달
    0.39
     prestige
    0.39
     unbear
    0.39
    POSITIVE LOGITS
    {
    0.53
    Accum
    0.50
    어가
    0.49
    内地
    0.49
    公园
    0.49
     inductance
    0.49
    utia
    0.49
    设备
    0.48
    ንዳ
    0.48
    ledged
    0.48
    Activations Density 0.000%

    No Known Activations