© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15371
    Prev
    Next
    INDEX
    Explanations

    easy, method, setProperty, classroom, hesitant

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

    That neuron fires most strongly on uncommon or content-heavy tokens—that is, words or symbols that are relatively rare and carry high informational weight in the document.

    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
     Skilled
    0.76
     выбира
    0.72
     родителей
    0.72
     nhạc
    0.71
     Voltaire
    0.71
     wikiHow
    0.70
     Comics
    0.70
     Hemp
    0.70
     lưng
    0.70
     Jersey
    0.69
    POSITIVE LOGITS
     categorical
    0.81
    ISATION
    0.79
     méth
    0.79
     stratification
    0.77
     northwestern
    0.76
     নববধূ
    0.75
    طة
    0.75
    श्मा
    0.74
     northern
    0.72
     deff
    0.70
    Activations Density 0.000%

    No Known Activations