© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3217
    Prev
    Next
    INDEX
    Explanations

    journal names

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

    This neuron detects numeric citation metadata (years, volume/issue numbers, page ranges) in academic references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    academic citations and bibliographic references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    academic journal citations and reference metadata (authors, years, journal titles, volumes/issues, pages) in scientific bibliographies.

    oai_token-act-pair · gpt-5Triggered 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
     гипсо
    0.64
    SessionFactory
    0.61
    gll
    0.61
    瑙
    0.60
    HTTPSampler
    0.59
    penguin
    0.58
    定向
    0.58
    钕
    0.58
    stopwords
    0.57
    ᓵ
    0.57
    POSITIVE LOGITS
     Journal
    1.52
     journal
    1.41
    Journal
    1.30
     journals
    1.20
     JOURNAL
    1.16
    journal
    1.08
     जर्नल
    1.01
     PLoS
    0.98
    JOUR
    0.96
     Journ
    0.95
    Activations Density 0.199%

    No Known Activations