© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91771
    Prev
    Next
    INDEX
    Explanations

    electric vehicles and cars

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects specific fuel‐ or energy‐type terms (e.g. electric, natural gas, CNG, hybrid, EV, NG).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    However
    -0.77
    Typical
    -0.76
     Reggio
    -0.72
    女の子
    -0.70
    Rö
    -0.69
    黴
    -0.69
     Typical
    -0.68
    这时候
    -0.68
     however
    -0.68
    cheduling
    -0.68
    POSITIVE LOGITS
     cars
    1.42
     vehicles
    1.40
     vehicle
    1.26
     propulsion
    1.09
     car
    1.09
     powered
    1.07
     voitures
    1.02
    powered
    1.00
     vehículos
    0.99
     véhicules
    0.95
    Activations Density 0.015%

    No Known Activations