© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77829
    Prev
    Next
    INDEX
    Explanations

    citations with years in parentheses

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

    The neuron is detecting bibliographic citation patterns, especially numeric volume, page, and year markers in scientific references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -1.97
     of
    -1.63
     didn
    -1.45
    which
    -1.43
     since
    -1.41
     for
    -1.36
     each
    -1.33
     also
    -1.27
     once
    -1.27
    </h2>
    -1.27
    POSITIVE LOGITS
     rafra
    1.57
     imprimer
    1.45
     réve
    1.39
     février
    1.38
     relâche
    1.38
     tromper
    1.36
     lourdes
    1.34
     avril
    1.33
     huile
    1.29
     rêver
    1.29
    Activations Density 0.052%

    No Known Activations