© 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. 2103
    Prev
    Next
    INDEX
    Explanations

    brown, field

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

    large portions

    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
    िलो
    0.49
     recibido
    0.47
     a
    0.46
    =[],
    0.46
     have
    0.46
     MO
    0.45
    ，
    0.44
    =[
    0.43
    ologous
    0.43
    ẻ
    0.43
    POSITIVE LOGITS
     piya
    0.54
     بڑے
    0.52
    мет
    0.50
     चलेगा
    0.50
     плана
    0.50
     देंगे
    0.48
     আমিন
    0.48
    itabbam
    0.48
    Animals
    0.48
    Lar
    0.47
    Activations Density 0.000%

    No Known Activations