© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191425
    Prev
    Next
    INDEX
    Explanations

    vehicles and destinations

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

    boolean property and convention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ما
    0.52
    вым
    0.52
    ৌর
    0.49
    體驗
    0.48
    سن
    0.47
    бая
    0.47
    ړ
    0.46
    상
    0.46
    sik
    0.45
    вы
    0.44
    POSITIVE LOGITS
     veículo
    0.60
     camion
    0.55
     veh
    0.51
     véhicules
    0.50
     veículos
    0.49
     Fleming
    0.48
     supervisor
    0.48
     véhicule
    0.48
     bookstore
    0.48
     wheelchair
    0.47
    Activations Density 0.000%

    No Known Activations