© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33362
    Prev
    Next
    INDEX
    Explanations

    numbers in citations

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

    The neuron is looking for standalone numeric tokens (digits), such as volume, page, or year numbers in 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_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
    glicher
    -1.05
    ETRY
    -0.99
    लो
    -0.98
    任何
    -0.98
     você
    -0.94
     muitas
    -0.94
     muestran
    -0.93
    taminophen
    -0.93
    髕
    -0.92
    quels
    -0.91
    POSITIVE LOGITS
    ticoli
    1.00
    ,
    0.98
     that
    0.97
     been
    0.95
    民宿
    0.95
    vature
    0.92
    具体的
    0.91
     chinoise
    0.91
    茨城
    0.91
    取决
    0.90
    Activations Density 0.002%

    No Known Activations