© 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. 35395
    Prev
    Next
    INDEX
    Explanations

    citations, references, and abbreviations

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

    The neuron activates on standalone numeric tokens (e.g. page/volume/issue numbers and other digit sequences in citations and URLs).

    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
     setelah
    -0.91
     北欧
    -0.91
    cznej
    -0.86
     pendaftaran
    -0.85
     chicco
    -0.85
     vecchio
    -0.84
    ٘
    -0.84
    rierten
    -0.83
     formData
    -0.83
     acts
    -0.82
    POSITIVE LOGITS
     quí
    1.04
     áng
    0.89
    itr
    0.87
     (!)
    0.84
     Ц
    0.84
     принце
    0.83
    PRESSION
    0.81
    (!)
    0.81
    corresponding
    0.80
    ryl
    0.80
    Activations Density 0.013%

    No Known Activations