© 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. 34-GEMMASCOPE-RES-131K
    7. 119335
    Prev
    Next
    INDEX
    Explanations

    citations with numbers

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

    The neuron strongly activates on reference‐style numeric tokens (citation numbers) inside brackets or footnote markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     actuel
    -0.94
     indien
    -0.93
    Ռ
    -0.90
     celda
    -0.88
    藁
    -0.87
     constate
    -0.85
    рию
    -0.84
     caract
    -0.83
     relleno
    -0.82
    ࿊
    -0.81
    POSITIVE LOGITS
     inserire
    0.88
     even
    0.82
    ),
    0.80
     Sahel
    0.78
     allegedly
    0.78
     supposedly
    0.77
     așa
    0.77
     kiểu
    0.76
    춤
    0.75
     resistenza
    0.74
    Activations Density 0.042%

    No Known Activations