© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1855
    Prev
    Next
    INDEX
    Explanations

    code comments and delimiters

    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
    rouw
    1.85
     petitioner
    1.63
    mane
    1.54
    pessoa
    1.51
     appellant
    1.49
    𝘱
    1.47
     Params
    1.47
    렌
    1.44
    casian
    1.44
     लॉ
    1.44
    POSITIVE LOGITS
     أما
    1.03
    خل
    0.91
    िता
    0.88
    ताल
    0.88
    Đ
    0.87
    hang
    0.87
    几个
    0.87
    ithing
    0.86
    Ị
    0.86
    ح
    0.86
    Activations Density 0.002%

    No Known Activations