© 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. 35819
    Prev
    Next
    INDEX
    Explanations

    vehicles or on state

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

    on a / on the

    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
    phosphorylation
    0.44
    ಕರಣ
    0.41
     antecedent
    0.41
    jose
    0.41
    }{
    0.40
     mediated
    0.40
     Wege
    0.39
    ouring
    0.38
    }{{
    0.38
    豊かな
    0.38
    POSITIVE LOGITS
     véhicules
    0.55
     розы
    0.51
     vehículos
    0.51
     vehicles
    0.49
     aigus
    0.49
     всех
    0.48
    车辆
    0.48
     автомобиля
    0.47
     structs
    0.46
     voitures
    0.46
    Activations Density 0.074%

    No Known Activations