© 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. 21675
    Prev
    Next
    INDEX
    Explanations

    legal citations and articles

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

    section of a legal text

    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
    四周
    0.52
     diperlukan
    0.47
     sejumlah
    0.44
     주변
    0.43
    >∕
    0.42
    หนึ่ง
    0.42
    בח
    0.41
    MenuActive
    0.41
     okolo
    0.41
     nécessaires
    0.41
    POSITIVE LOGITS
     this
    0.51
     the
    0.47
     Agenda
    0.47
     проекта
    0.46
     which
    0.44
     Harvard
    0.43
    娣
    0.41
     ibid
    0.41
     Bldg
    0.40
     Nal
    0.40
    Activations Density 0.067%

    No Known Activations