© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60875
    Prev
    Next
    INDEX
    Explanations

    motor vehicle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ("
    0.40
    KURZBESCHREIBUNG
    0.40
     "$
    0.39
     ["
    0.39
    unica
    0.39
     Scissors
    0.39
    ПР
    0.38
    stringProp
    0.38
    wss
    0.37
     -"
    0.37
    POSITIVE LOGITS
     vehicle
    1.92
     vehicles
    1.83
    vehicle
    1.80
     Vehicle
    1.73
     Vehicles
    1.70
    vehicles
    1.70
    Vehicle
    1.67
     veículos
    1.66
     véhicules
    1.66
     véhicule
    1.64
    Activations Density 0.003%

    No Known Activations