© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48330
    Prev
    Next
    INDEX
    Explanations

    motorcycles or scooters

    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
    avigation
    -0.69
     Od
    -0.69
     Betty
    -0.66
    趾
    -0.65
     boo
    -0.65
     össze
    -0.65
     Traditional
    -0.64
     Audi
    -0.64
     Phelps
    -0.64
    力が
    -0.63
    POSITIVE LOGITS
     scooter
    1.48
     scooters
    1.34
     Scooter
    1.19
    scooter
    1.02
     Vespa
    0.96
    Scooter
    0.94
     bebek
    0.90
     cubs
    0.87
     Zuma
    0.85
     Cubs
    0.84
    Activations Density 0.029%

    No Known Activations