© 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. 199079
    Prev
    Next
    INDEX
    Explanations

    seasons before fall

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

    fraud detection

    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
    a
    0.50
     राधे
    0.49
    aec
    0.46
    ShaderType
    0.46
     मनु
    0.45
    頖
    0.45
    兕
    0.45
    Renderer
    0.44
    γω
    0.44
     رياضيات
    0.44
    POSITIVE LOGITS
    е
    0.53
     ethyl
    0.51
     kisah
    0.51
     encompass
    0.49
    и
    0.48
     purchasers
    0.48
     two
    0.47
     sellers
    0.47
    長く
    0.47
     delle
    0.47
    Activations Density 0.000%

    No Known Activations