© 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. 43836
    Prev
    Next
    INDEX
    Explanations

    origin and sourcing locations

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

    sourcing and manufacturing origin

    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
    溶液
    0.49
     bức
    0.45
    指数
    0.45
     bestow
    0.45
    卷积
    0.44
     nourishment
    0.43
     éduc
    0.43
    謬
    0.42
    深く
    0.42
     immisc
    0.42
    POSITIVE LOGITS
    供应商
    0.83
     suppliers
    0.82
     China
    0.77
     supplier
    0.75
     sourced
    0.72
    supplier
    0.71
     outsourced
    0.70
    suppliers
    0.70
    China
    0.67
     sourcing
    0.66
    Activations Density 0.102%

    No Known Activations