© 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. 13594
    Prev
    Next
    INDEX
    Explanations

    Company Stock, combination of

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

    The neuron strongly activates on standalone numeric tokens (e.g. volume, page, year, or issue numbers) in reference and citation 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
     you
    -0.98
     arxiv
    -0.91
     because
    -0.88
    inematics
    -0.86
    ilderness
    -0.85
     مساب
    -0.84
     tenerife
    -0.84
     milioni
    -0.82
     like
    -0.82
    ಖ
    -0.82
    POSITIVE LOGITS
     relacionada
    1.06
    骉
    1.03
     ráp
    1.03
     rapidement
    0.95
     dán
    0.94
     Turquie
    0.93
     Lý
    0.93
    ∛
    0.92
     Wirkungen
    0.91
    jų
    0.90
    Activations Density 0.002%

    No Known Activations