© 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. 111018
    Prev
    Next
    INDEX
    Explanations

    road trips and driving

    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
     walk
    -1.00
    walks
    -1.00
    walking
    -0.98
    Walk
    -0.97
    Walking
    -0.97
     walker
    -0.97
     walking
    -0.96
    walker
    -0.96
     walks
    -0.95
    Downtown
    -0.92
    POSITIVE LOGITS
     driving
    2.03
    driving
    1.95
     highway
    1.95
     Driving
    1.82
     road
    1.80
     highways
    1.76
    Driving
    1.70
     carretera
    1.66
     roads
    1.60
    ขับ
    1.57
    Activations Density 0.046%

    No Known Activations