© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38833
    Prev
    Next
    INDEX
    Explanations

    code or programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indivíduos
    -1.81
    
    -1.65
     cial
    -1.62
    ものである
    -1.61
     his
    -1.58
     カジュアル
    -1.55
     jego
    -1.55
    컹
    -1.55
    ton
    -1.54
     hk
    -1.54
    POSITIVE LOGITS
     with
    1.98
    7
    1.72
     or
    1.67
     for
    1.63
     There
    1.61
     áreas
    1.52
     which
    1.50
     if
    1.48
     große
    1.48
    Spesifikasi
    1.45
    Activations Density 0.003%

    No Known Activations