© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 462
    Prev
    Next
    INDEX
    Explanations

    design, mechanisms, and circuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     iconos
    1.83
    敤
    1.67
     Holi
    1.65
     fomentar
    1.53
    اؤ
    1.52
    🤳
    1.50
    섦
    1.50
     üy
    1.49
     jueces
    1.47
     Outreach
    1.47
    POSITIVE LOGITS
     engine
    1.87
     shaft
    1.82
     machinery
    1.81
     gearbox
    1.78
     valve
    1.75
     engines
    1.72
    valve
    1.63
     torque
    1.59
     crankshaft
    1.56
    engine
    1.55
    Activations Density 0.950%

    No Known Activations