© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15877
    Prev
    Next
    INDEX
    Explanations

    smoking, tobacco, and cessation

    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
    𝗿
    2.10
    𝗮
    2.08
    ரி
    2.03
    𝗶
    1.88
    𝘀
    1.88
    ifical
    1.87
    𝗼
    1.78
    du
    1.75
    gani
    1.73
    ваем
    1.72
    POSITIVE LOGITS
    囪
    2.34
    ות
    2.20
    囱
    2.17
    htra
    2.15
    මත්
    2.02
     পড়েছে
    2.02
    ̆
    1.95
     ultricies
    1.91
    ছে
    1.87
    اریخ
    1.86
    Activations Density 0.104%

    No Known Activations