© 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. 65555
    Prev
    Next
    INDEX
    Explanations

    manufacturer, compatibility, options

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

    potentially with extensions

    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
     अभिनंदन
    0.56
     KIND
    0.50
     అంటూ
    0.48
     January
    0.47
    णी
    0.47
     Dictionary
    0.47
     Peter
    0.46
     ["
    0.46
     setzt
    0.46
     來
    0.46
    POSITIVE LOGITS
    وسیع
    0.47
    ۵
    0.45
     adequ
    0.44
    تميز
    0.44
    uelve
    0.43
    études
    0.43
    setVerticalGroup
    0.42
    ផ្តល់
    0.42
    itudini
    0.41
    ologist
    0.41
    Activations Density 0.001%

    No Known Activations