© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11944
    Prev
    Next
    INDEX
    Explanations

    notes for

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron specializes in spotting occurrences of the word “note” (including plural “notes”) in contexts like course notes, class notes, or note listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    م
    1.05
    advert
    0.96
    ز
    0.95
    ن
    0.89
    reason
    0.87
    نا
    0.85
    mits
    0.85
    ע
    0.84
    Hora
    0.82
    COMMIT
    0.81
    POSITIVE LOGITS
    MinIntensity
    0.91
    就行
    0.90
     এক্ষেত্রে
    0.88
    誒
    0.86
    ृ
    0.86
    ின
    0.85
    षद
    0.84
    ствия
    0.84
     ও
    0.84
    ль
    0.83
    Activations Density 0.011%

    No Known Activations