© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2290
    Prev
    Next
    INDEX
    Explanations

    math operators and code syntax

    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
    =[],
    0.66
    #,
    0.64
    =['
    0.63
    kwargs
    0.61
    [:
    0.61
    .__
    0.60
    getitem
    0.58
    (['
    0.57
    =[]
    0.56
    [:]
    0.53
    POSITIVE LOGITS
     -(
    0.83
     *((
    0.78
     /(
    0.75
     +(
    0.73
    +(
    0.72
     *(
    0.69
     angust
    0.68
     /$
    0.67
    *(
    0.66
    *((
    0.66
    Activations Density 0.003%

    No Known Activations