© 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. 10249
    Prev
    Next
    INDEX
    Explanations

    some, others, another

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

    This neuron activates on general quantifier words that refer to unspecified subsets (e.g. some, others, most, few, ones, half).

    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
     first
    0.72
     a
    0.70
    하지만
    0.70
     Primeiro
    0.69
    はじめ
    0.68
    לה
    0.68
     اے
    0.67
     orange
    0.66
    첫
    0.66
    ان
    0.65
    POSITIVE LOGITS
     purporting
    0.68
     हिस्सों
    0.67
    gna
    0.66
    encers
    0.66
     जगहों
    0.64
    ঙ্কে
    0.64
    یداری
    0.63
    erdapat
    0.63
     litigants
    0.63
    煊
    0.63
    Activations Density 0.264%

    No Known Activations