© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10527
    Prev
    Next
    INDEX
    Explanations

    generate specific number

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

    The neuron fires on the typographic right single quotation mark (curly apostrophe) used in contractions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the contraction "It's" at the beginning of a sentence or document.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    the typographic right apostrophe (’) used in English contractions and possessives.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     a
    1.03
     the
    0.95
    </h3>
    0.93
     to
    0.93
     \
    0.91
    0.91
     it
    0.89
     {
    0.89
     for
    0.88
     e
    0.88
    POSITIVE LOGITS
    
    0.88
     Парт
    0.87
    geoning
    0.86
    percayaan
    0.84
    
    0.84
    ⺠
    0.84
    滖
    0.84
     ҳу
    0.83
    striatis
    0.83
    頩
    0.83
    Activations Density 0.002%

    No Known Activations