© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    The neuron strongly activates on formal, bureaucratic or regulatory language—especially notices requesting approvals, public comments, or invoking high-level procedural terms.

    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
     erzählen
    0.66
     conclusão
    0.58
     moeten
    0.56
     erzählt
    0.56
    즙
    0.56
    תה
    0.53
     மாநில
    0.53
     ತಪ್ಪ
    0.52
     निष्कर्ष
    0.52
     اقول
    0.52
    POSITIVE LOGITS
    ↵
    0.70
    ↵↵
    0.59
    <eos>
    0.54
     ###
    0.51
     hole
    0.50
    ↵↵↵↵
    0.49
     Speck
    0.49
    ���
    0.49
     towed
    0.48
     androidx
    0.48
    Activations Density 0.000%

    No Known Activations