© 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. 4581
    Prev
    Next
    INDEX
    Explanations

    grammar and errors

    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
    鎴
    2.00
    ERICA
    1.95
     “‘
    1.89
    
    1.87
     menikah
    1.86
    ￠
    1.81
    岨
    1.80
    HttpResponse
    1.80
     jantung
    1.79
    KindOfClass
    1.77
    POSITIVE LOGITS
    s
    2.03
    es
    1.98
    ের
    1.67
    "+
    1.66
    ing
    1.56
    sop
    1.52
    sites
    1.46
    um
    1.42
    ции
    1.40
     "
    1.36
    Activations Density 0.792%

    No Known Activations