© 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. 12394
    Prev
    Next
    INDEX
    Explanations

    be able to be

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

    This neuron fires on the copular verb “be” (and its inflected forms like “being,” “to be,” 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
    1.41
    ls
    1.22
     imprescind
    1.19
    nicht
    1.15
     byli
    1.14
     eigentlich
    1.13
    OUT
    1.13
     keine
    1.13
    map
    1.12
    cus
    1.12
    POSITIVE LOGITS
    ко
    1.10
     reimbursed
    1.07
     able
    1.00
    اب
    1.00
     phép
    0.99
    ষ্টিত
    0.98
    褥
    0.98
     modernized
    0.97
    ekeeping
    0.96
    স
    0.95
    Activations Density 0.238%

    No Known Activations