© 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. 971
    Prev
    Next
    INDEX
    Explanations

    and or

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

    The neuron responds to author names (proper surnames) in academic‐style bibliographic citations.

    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
    <unused2223>
    0.54
    ელია
    0.52
    <unused406>
    0.51
    ওনা
    0.50
    狐
    0.49
    <unused2221>
    0.49
    <unused654>
    0.48
    九
    0.47
    ल्हा
    0.47
    യാ
    0.46
    POSITIVE LOGITS
    ،
    0.77
     ਅਤੇ
    0.66
     amerikanischen
    0.65
     ameryka
    0.65
     vuonna
    0.63
     statunitense
    0.63
    ®,
    0.62
     येथे
    0.61
     Verlag
    0.60
     ایالات
    0.59
    Activations Density 0.399%

    No Known Activations