© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127961
    Prev
    Next
    INDEX
    Explanations

    This neuron detects section headings that begin with a four-digit year (e.g. “2013:”) at the start of a line.

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

    2013 event titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varios
    -1.30
    ventajas
    -1.28
     sudadera
    -1.17
    during
    -1.16
    tableLayoutPanel
    -1.14
    绉
    -1.13
    seitigen
    -1.13
    Kedves
    -1.09
    bước
    -1.09
     different
    -1.09
    POSITIVE LOGITS
    .
    1.28
    ↵
    1.11
    (
    1.08
    报记者
    1.02
    ."
    1.02
    <em>
    1.01
    ?
    0.98
     LIVER
    0.98
     KRA
    0.97
    。　　
    0.95
    Activations Density 0.063%

    No Known Activations