© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2318
    Prev
    Next
    INDEX
    Explanations

    number followed by unit

    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_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
     Marriage
    1.16
     marriages
    1.07
     更
    1.06
     Amazing
    1.06
     Outreach
    1.05
     commencement
    1.05
     spécifiques
    1.05
     JUNE
    1.03
     福
    1.03
     Provinces
    1.02
    POSITIVE LOGITS
    Чтобы
    1.01
    getCount
    0.97
    ână
    0.96
    ügel
    0.93
    asă
    0.91
    rean
    0.90
    flox
    0.89
    бат
    0.89
    getLong
    0.89
    ioid
    0.88
    Activations Density 0.114%

    No Known Activations