© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    language particles

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

    The neuron fires on content words that are specific names or titles—i.e. proper nouns like gallery or exhibition names, place names, artist names, brand/model names, etc.

    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
    相关的
    0.68
     तक
    0.68
    that
    0.68
     arası
    0.67
    अच्छा
    0.65
    权限
    0.64
     پیسے
    0.63
     arasında
    0.63
    কেই
    0.62
    את
    0.62
    POSITIVE LOGITS
     비롯
    1.03
     있고
    0.99
     포함
    0.95
     되지
    0.91
     있었
    0.89
    되지
    0.88
    されていない
    0.88
     중심으로
    0.87
     없다
    0.86
     보인다
    0.83
    Activations Density 0.007%

    No Known Activations