© 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. 10654
    Prev
    Next
    INDEX
    Explanations

    period

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

    The neuron activates on explicit “Period” tokens used as end-of-sentence markers.

    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
    ែ
    0.63
     culprit
    0.63
     वनडे
    0.59
    IODevice
    0.59
     Analyzing
    0.58
    perluan
    0.57
     didactic
    0.57
    лната
    0.56
     ஆண்டுகள்
    0.56
     isomeric
    0.55
    POSITIVE LOGITS
    fers
    0.65
    퐁
    0.59
    ically
    0.59
    ként
    0.57
    ंकडून
    0.57
    PSP
    0.57
    nlp
    0.57
     acteur
    0.57
    PERIOD
    0.56
    polis
    0.55
    Activations Density 0.004%

    No Known Activations