© 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. 2393
    Prev
    Next
    INDEX
    Explanations

    articles ending in common prepositions

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

    The neuron fires on the stems of common English contractions (e.g. the part before the apostrophe in you’re, aren’t, weren’t).

    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
     deprecated
    0.46
     canonical
    0.43
     creo
    0.40
    lbrakk
    0.39
     উনি
    0.38
     piu
    0.38
    /
    0.38
     corresponding
    0.38
     elaboration
    0.38
     linearly
    0.37
    POSITIVE LOGITS
     Oprah
    0.41
    uncie
    0.40
    ophe
    0.39
    Aprend
    0.39
    stown
    0.38
    árny
    0.38
    抖
    0.38
    ješ
    0.38
    andering
    0.38
    Ă
    0.38
    Activations Density 0.000%

    No Known Activations