© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 289
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

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

    The neuron is primarily detecting numeric tokens (e.g. measurements, citation labels, years, and other 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
     fortfarande
    -0.97
     Warszawie
    -0.93
    StoreMessageInfo
    -0.90
     koszt
    -0.90
     ДТП
    -0.89
     betweenstory
    -0.87
     повече
    -0.87
    貴重
    -0.86
    loyds
    -0.84
     inappropriés
    -0.83
    POSITIVE LOGITS
    qc
    0.96
    eri
    0.90
     통해
    0.85
     pug
    0.84
     Pug
    0.82
    ibia
    0.79
    PARTIC
    0.78
    žená
    0.78
    Varios
    0.77
    剩
    0.76
    Activations Density 0.233%

    No Known Activations