© 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. 16441
    Prev
    Next
    INDEX
    Explanations

    car make, model, type

    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
     there
    -1.39
     
    -1.20
     fundamenta
    -1.16
    aried
    -1.14
     minha
    -1.12
     dout
    -1.12
     escon
    -1.09
     jeho
    -1.09
     it
    -1.09
     pós
    -1.08
    POSITIVE LOGITS
     manufacturers
    1.46
     hvil
    1.41
     brands
    1.34
     maksi
    1.32
     technisch
    1.27
     manufacturer
    1.27
     kela
    1.26
     of
    1.25
     specifications
    1.24
     erfaren
    1.24
    Activations Density 0.019%

    No Known Activations