© 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. 63852
    Prev
    Next
    INDEX
    Explanations

    car generations

    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
     shimano
    -1.35
     yamaha
    -1.33
     piaggio
    -1.26
     ducati
    -1.19
     isuzu
    -1.16
     nikon
    -1.16
     michelin
    -1.16
     lamborghini
    -1.14
     toshiba
    -1.13
     garmin
    -1.13
    POSITIVE LOGITS
     Civic
    1.64
     civic
    1.47
    Civic
    1.38
     Dodge
    1.26
     cars
    1.23
     Mustang
    1.23
    civic
    1.22
     Ford
    1.17
    Dodge
    1.17
     Golf
    1.13
    Activations Density 0.080%

    No Known Activations