© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3078
    Prev
    Next
    INDEX
    Explanations

    many + noun

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

    The neuron detects instances of the word “many” (especially when used as a sentence-initial quantifier).

    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
    });
    0.81
    EST
    0.77
     Ejec
    0.77
    |\
    0.76
     Auss
    0.76
    id
    0.75
    0.75
     digitized
    0.73
     فنا
    0.73
    يات
    0.71
    POSITIVE LOGITS
    в
    1.13
    ﺹ
    1.03
    י
    1.02
    נו
    1.01
    不愿意
    0.95
    不但
    0.95
    ธุ์
    0.94
    ్
    0.94
    ла
    0.93
     lắm
    0.93
    Activations Density 0.012%

    No Known Activations