© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92410
    Prev
    Next
    INDEX
    Explanations

    car sedans

    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
     весело
    -0.81
     abierta
    -0.79
     Bronco
    -0.75
     harina
    -0.74
    スズキ
    -0.74
    layed
    -0.72
     bronco
    -0.72
     Corbu
    -0.71
     HAMILTON
    -0.70
     Tiny
    -0.69
    POSITIVE LOGITS
     sedan
    1.34
     luxury
    1.17
     executive
    1.10
     Sedan
    0.98
     BMW
    0.95
     sed
    0.95
     Luxury
    0.94
    Lux
    0.88
     бизнес
    0.86
    lux
    0.85
    Activations Density 0.020%

    No Known Activations