© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13555
    Prev
    Next
    INDEX
    Explanations

    module initialization

    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_7_width_16k_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
    consulta
    1.99
    ∠
    1.86
    НЕ
    1.84
    не
    1.82
     herpes
    1.78
    sword
    1.78
    プチ
    1.75
    สิ่งที่
    1.75
    bsc
    1.75
    と思って
    1.74
    POSITIVE LOGITS
    ি
    1.77
    척
    1.71
     বিষয়ক
    1.69
     Öffentlich
    1.63
    ”।
    1.56
    ਂ
    1.56
    덕
    1.54
     postale
    1.53
     공동
    1.51
     부여
    1.51
    Activations Density 0.001%

    No Known Activations