© 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. 72552
    Prev
    Next
    INDEX
    Explanations

    initials followed by punctuation

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

    The neuron fires on the single‐ or two‐letter capital tokens that mark author initials in citation reference lists.

    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
     fêtes
    -1.02
    íram
    -0.94
     relato
    -0.93
    actrice
    -0.87
     comprimidos
    -0.86
     kuten
    -0.86
     EXISTS
    -0.85
    евна
    -0.85
     nyelv
    -0.84
    fancybox
    -0.84
    POSITIVE LOGITS
     and
    1.00
    iency
    0.91
    🟧
    0.89
    達の
    0.86
     November
    0.85
     éste
    0.83
    Ottimo
    0.82
    迥
    0.82
     Williamsburg
    0.81
     April
    0.80
    Activations Density 0.007%

    No Known Activations