© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127937
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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_22/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
    TYPE
    -0.85
    ::::::::
    -0.83
    ::::
    -0.82
    مثل
    -0.82
    TYPED
    -0.81
    -0.79
     Calculus
    -0.79
     Profession
    -0.79
     limousine
    -0.79
    希
    -0.78
    POSITIVE LOGITS
     cheap
    1.02
    伟大的
    1.01
     nampak
    0.98
     rẻ
    0.97
     municipal
    0.96
    rabbitmq
    0.96
     befes
    0.95
     inexpensive
    0.94
    lcccccc
    0.92
     peasant
    0.92
    Activations Density 0.124%

    No Known Activations