© 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. 10509
    Prev
    Next
    INDEX
    Explanations

    manufacturer, supplier, exporter

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

    government statistics and skiing

    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
    大
    0.51
    約
    0.50
    （
    0.48
    常見
    0.47
    如今
    0.47
    很多
    0.46
     COMMON
    0.45
     यहाँ
    0.44
    院
    0.43
    権
    0.42
    POSITIVE LOGITS
     bespoke
    0.53
     tweezers
    0.52
     tensile
    0.51
     podium
    0.48
     ferro
    0.48
     forklift
    0.48
     masked
    0.46
     visage
    0.46
     medal
    0.45
     apostle
    0.45
    Activations Density 0.001%

    No Known Activations