© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95832
    Prev
    Next
    INDEX
    Explanations

    case citations after names/titles

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

    The neuron fires on standalone numeric tokens in reference or citation entries, such as page numbers, years, and volume/issue numbers.

    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
     at
    -1.09
     when
    -1.06
     activities
    -0.96
     which
    -0.93
     senso
    -0.92
    prefs
    -0.88
    </td>
    -0.88
    ření
    -0.87
    unchecked
    -0.86
    ríamos
    -0.84
    POSITIVE LOGITS
    cellor
    1.12
    anei
    1.05
    doesn
    0.96
     marvelous
    0.94
     resaltar
    0.93
     astonishing
    0.92
    didn
    0.91
    harusnya
    0.91
    excellents
    0.91
    SPARENT
    0.91
    Activations Density 0.003%

    No Known Activations