© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87150
    Prev
    Next
    INDEX
    Explanations

    casino game

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

    core knowledge cut-off

    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
    Negative Logits
    Pref
    0.52
     അവിടെ
    0.49
    半分
    0.48
     ulterior
    0.48
     insofar
    0.48
     в
    0.47
    䉍
    0.46
    ᵖ
    0.46
    SimpleDateFormat
    0.45
    horizontalLayout
    0.45
    POSITIVE LOGITS
     Meals
    0.48
     metallurgical
    0.46
     Sellers
    0.45
    urt
    0.45
     metallurgy
    0.45
     Designation
    0.44
     crossroads
    0.44
     Melvin
    0.43
     Industria
    0.43
     nitric
    0.43
    Activations Density 0.000%

    No Known Activations