© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    a lot of

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

    The neuron strongly activates on the quantifier phrase “a lot (of),” i.e. expressions indicating “a lot of.”

    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
     todas
    0.95
    𝑻
    0.88
     vuoi
    0.85
     terrifying
    0.84
    录取
    0.84
    posterous
    0.84
     Utilizing
    0.83
     adegu
    0.83
     Unternehmens
    0.82
     उज्ज
    0.80
    POSITIVE LOGITS
    ת
    1.01
    rát
    0.88
    '$,
    0.87
    <bos>
    0.86
    gens
    0.86
    汢
    0.84
    เจน
    0.82
    หลาย
    0.81
    дная
    0.81
    Oku
    0.81
    Activations Density 0.085%

    No Known Activations