© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13711
    Prev
    Next
    INDEX
    Explanations

    loop index 'i'

    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
     stomach
    0.98
    ার্ট
    0.95
     Stomach
    0.91
    ισμό
    0.89
    Remainder
    0.88
    狄
    0.87
     dziś
    0.87
     গ্রে
    0.85
    াহিত
    0.84
    理
    0.83
    POSITIVE LOGITS
    combin
    0.89
    ضاع
    0.88
    facet
    0.86
     facet
    0.86
    nested
    0.84
     مرب
    0.81
    kanie
    0.79
    uba
    0.79
    oodle
    0.77
    连续
    0.77
    Activations Density 0.089%

    No Known Activations