© 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. 82
    Prev
    Next
    INDEX
    Explanations

    mortal

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

    The neuron strongly activates on punctuation marks (especially commas and periods) and adjacent common function words, effectively detecting sentence‐boundary and punctuation tokens.

    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_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
    ㅁ
    0.34
    =
    0.33
    ```
    0.33
    @
    0.33
    _
    0.32
    $('.
    0.32
    🙍
    0.32
    (
    0.31
    .。
    0.31
    。
    0.31
    POSITIVE LOGITS
     Although
    0.55
     Often
    0.53
     Obwohl
    0.51
     There
    0.50
     However
    0.50
     Whether
    0.49
     Even
    0.48
     While
    0.47
     Unlike
    0.47
     Bahkan
    0.47
    Activations Density 2.953%

    No Known Activations