© 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. 8190
    Prev
    Next
    INDEX
    Explanations

    input and output C++

    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
    ição
    1.60
    alba
    1.60
    oló
    1.60
    𝒂
    1.51
    ০
    1.49
    ா
    1.46
     Și
    1.41
    ária
    1.41
    𝒆
    1.38
    asem
    1.37
    POSITIVE LOGITS
     isActive
    1.70
     кла
    1.65
    juna
    1.64
    邮
    1.56
     울
    1.55
    linestyle
    1.54
    굵
    1.52
    обходимо
    1.52
    雳
    1.51
    /^
    1.50
    Activations Density 0.001%

    No Known Activations