© 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-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2265
    Prev
    Next
    INDEX
    Explanations

    your health and treatment advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    orent
    0.70
     kissed
    0.69
    प्रति
    0.67
    सह
    0.66
     kisses
    0.66
     shall
    0.65
     지
    0.65
    ोल
    0.65
     कृत
    0.64
     Handwritten
    0.64
    POSITIVE LOGITS
    壢
    0.69
    到了
    0.68
     দশকের
    0.68
    اءِ
    0.64
    óta
    0.62
    庁
    0.60
    motionProxy
    0.60
    秉
    0.59
    웰
    0.59
     Ủy
    0.59
    Activations Density 0.021%

    No Known Activations