© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14482
    Prev
    Next
    INDEX
    Explanations

    citations with numbers and names

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

    The neuron detects bibliographic citation elements, especially numbers (years, volume/page figures) and related punctuation in reference entries.

    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
     by
    -1.06
     FOR
    -1.05
     siker
    -1.04
     stratég
    -1.03
     oyunu
    -1.02
     strategies
    -1.02
     tevé
    -1.02
     Time
    -1.01
     instructional
    -1.01
     ngược
    -1.00
    POSITIVE LOGITS
     gravi
    1.32
     dispen
    1.27
    jamento
    1.25
     rower
    1.22
     centrif
    1.20
     TEMPO
    1.20
     electrica
    1.20
     attent
    1.19
     cori
    1.18
     monti
    1.18
    Activations Density 0.003%

    No Known Activations