© 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. 116867
    Prev
    Next
    INDEX
    Explanations

    increased costs, offer, capacity, find

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

    current events

    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
     FBI
    0.52
     –
    0.49
     CHEMICAL
    0.49
     стиль
    0.47
    /
    0.47
     «
    0.46
     »
    0.46
    ៉
    0.46
    United
    0.45
    FBI
    0.45
    POSITIVE LOGITS
     Voyages
    0.50
     topography
    0.50
     دوی
    0.49
     それぞれ
    0.49
    zczeg
    0.49
    稒
    0.49
     topographical
    0.48
     চক্ষে
    0.48
     voluptates
    0.48
     renderEncoder
    0.47
    Activations Density 0.001%

    No Known Activations