© 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. 65037
    Prev
    Next
    INDEX
    Explanations

    Business and companies

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

    alphabetical sequences * orchestrating * creating pathways

    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
     Seja
    0.50
    gens
    0.46
    did
    0.45
    relations
    0.45
    isna
    0.44
     IUnary
    0.44
     只
    0.43
     Ehm
    0.41
     INDIRECT
    0.41
     এস
    0.40
    POSITIVE LOGITS
     manufacturer
    0.51
    製造
    0.49
     CEOs
    0.48
     manufacturers
    0.45
    ผลิตภัณฑ์
    0.44
    ﮧ
    0.44
     الولايات
    0.44
     Costco
    0.44
     আমেরিক
    0.43
     vállalat
    0.43
    Activations Density 0.001%

    No Known Activations