© 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. 34-GEMMASCOPE-RES-131K
    7. 48602
    Prev
    Next
    INDEX
    Explanations

    division questions

    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_34/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
    新浪
    -0.91
     unless
    -0.78
     جيدة
    -0.78
    鈕
    -0.75
    Unless
    -0.75
     samman
    -0.75
    outros
    -0.75
     olímp
    -0.75
    percentage
    -0.74
    actividad
    -0.73
    POSITIVE LOGITS
    Tib
    0.81
     Resili
    0.79
    begin
    0.77
    ParallelGroup
    0.77
    룡
    0.77
     resiliency
    0.76
     valign
    0.73
    ida
    0.73
    ibase
    0.73
    mtable
    0.73
    Activations Density 0.005%

    No Known Activations