© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8716
    Prev
    Next
    INDEX
    Explanations

    prepositions after verbs

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

    The neuron strongly activates on standalone numbers and numeric tokens (e.g. section and legislative citation numbers).

    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
    ěné
    0.82
    sulfonyl
    0.80
     Dispose
    0.79
     danos
    0.77
    ignores
    0.77
     Empires
    0.77
    徊
    0.77
     शोक
    0.76
    蚪
    0.75
    아요
    0.75
    POSITIVE LOGITS
    et
    0.93
     for
    0.84
     up
    0.81
     as
    0.79
     at
    0.75
    der
    0.73
     representing
    0.73
    de
    0.72
    ছেন
    0.72
     by
    0.72
    Activations Density 0.001%

    No Known Activations