© 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. 4479
    Prev
    Next
    INDEX
    Explanations

    **Detecting verb 'be' forms**

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

    The neuron activates on numeric tokens (quantities, counts, monetary amounts, etc.).

    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
    ة
    1.45
    rdquo
    1.30
    นิยม
    1.27
    ري
    1.27
    larda
    1.27
    re
    1.24
    mis
    1.23
    ra
    1.20
    reg
    1.20
    nicht
    1.20
    POSITIVE LOGITS
    ف
    1.23
    но
    1.09
     laptop
    1.07
     presto
    1.07
    있
    1.06
    이가
    1.04
    ۥ
    1.03
    엠
    1.01
    ко
    0.98
     dotycz
    0.98
    Activations Density 0.378%

    No Known Activations