© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7757
    Prev
    Next
    INDEX
    Explanations

    python code examples

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

    The neuron is keyed to full-stop punctuation, i.e. sentence-ending periods.

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

    periods that mark the end of sentences or sections, particularly in formatted or structured text.

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

    punctuation and typographic symbols, especially sentence/clause delimiters like end-of-sentence marks and other separators.

    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
    HandleFunc
    0.57
     {:?}",
    0.57
    흔
    0.55
     hablan
    0.55
     नव्हते
    0.53
    вка
    0.53
     Frege
    0.53
     Advis
    0.52
    іо
    0.52
    CB
    0.52
    POSITIVE LOGITS
    Serializer
    0.57
     queryset
    0.57
     serializers
    0.55
    queryset
    0.52
     सोर्स
    0.51
     suç
    0.50
    attrs
    0.50
     과
    0.49
     zdroj
    0.49
     ওভার
    0.49
    Activations Density 0.002%

    No Known Activations