© 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. 2476
    Prev
    Next
    INDEX
    Explanations

    added intensifier "too"

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

    The neuron fires specifically on the adverb “too.”

    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
    ่
    1.30
    ्स
    1.16
    ্লাহ
    1.15
     dotycz
    1.13
    𝙚
    1.10
    يين
    1.02
    एचओ
    1.02
     обязан
    1.00
    
    1.00
    ताओं
    0.99
    POSITIVE LOGITS
    너무
    1.27
    o
    1.20
    ot
    1.16
     불구하고
    1.07
    oos
    1.03
    ंग
    0.96
    aş
    0.96
    oš
    0.96
    om
    0.95
    多的
    0.95
    Activations Density 0.026%

    No Known Activations