© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    numbers and conjunctions like 'since', 'until', 'close'

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

    dates and classifications

    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
     ನನ್ನ
    0.54
     Vestone
    0.51
     Ztg
    0.51
     Sereth
    0.51
    asambhavam
    0.50
    贰百
    0.50
    鏻
    0.48
     RasterModelGrid
    0.48
     సు
    0.48
     对于
    0.46
    POSITIVE LOGITS
    also
    0.55
     Americans
    0.55
     American
    0.52
     US
    0.50
    known
    0.49
    0.48
     America
    0.47
     amerik
    0.47
    ually
    0.46
         
    0.46
    Activations Density 0.096%

    No Known Activations