© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12975
    Prev
    Next
    INDEX
    Explanations

    punctuation following words

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

    The neuron strongly responds to common function words—especially conjunctions, prepositions, and other “stopwords” that structure clauses (e.g. however, of, with, the, not, after).

    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_24_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
    ،
    0.95
    )،
    0.91
    と共に
    0.82
    "،
    0.80
    ፣
    0.78
    。,
    0.76
    ,//
    0.75
    ၊
    0.73
    ，
    0.72
    ﹚
    0.72
    POSITIVE LOGITS
    这一切
    0.77
    সমস্ত
    0.71
     everybody
    0.70
     resurrect
    0.69
     EVERYTHING
    0.69
    I
    0.66
    诸多
    0.66
     সবই
    0.65
    ങ്ങളിൽ
    0.64
     wszyscy
    0.64
    Activations Density 0.188%

    No Known Activations