© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77205
    Prev
    Next
    INDEX
    Explanations

    CPU instruction prefixes and numerical types

    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
     desem
    -0.73
     Nagy
    -0.71
     сні
    -0.70
     lam
    -0.69
    先后
    -0.68
    lun
    -0.67
     lun
    -0.66
    Uno
    -0.66
     dye
    -0.66
    öng
    -0.66
    POSITIVE LOGITS
     międzynarod
    0.76
     Direito
    0.75
     float
    0.73
     {
    0.73
     meille
    0.73
    天使
    0.73
    整数
    0.70
     circumscribed
    0.70
     nighttime
    0.70
     sociologists
    0.69
    Activations Density 0.017%

    No Known Activations