© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 300
    Prev
    Next
    INDEX
    Explanations

    punctuation and labels

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

    This neuron detects standalone punctuation tokens (e.g., quotation marks, hyphens, apostrophes).

    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
    -
    0.38
     y
    0.36
     B
    0.35
    ,
    0.35
     word
    0.34
     van
    0.34
     graffiti
    0.34
      
    0.34
     t
    0.34
     "
    0.33
    POSITIVE LOGITS
    血糖
    0.44
     CharPtr
    0.38
     TestAvg
    0.37
     hyperglycemia
    0.36
    第壹百
    0.34
     hypergly
    0.34
     স্বীক
    0.34
     Hesap
    0.34
     Endocrinology
    0.34
     Glucose
    0.33
    Activations Density 0.401%

    No Known Activations