© 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. 65936
    Prev
    Next
    INDEX
    Explanations

    citations with bracketed numbers

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

    The neuron responds to standalone numeric tokens (e.g., years, reference numbers, counts).

    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
     مصرى
    -0.89
    ЕР
    -0.79
     ocasiones
    -0.77
    KJV
    -0.76
     Keats
    -0.75
     masih
    -0.75
     conscientes
    -0.75
     Walkover
    -0.74
    still
    -0.74
     KJV
    -0.73
    POSITIVE LOGITS
     until
    1.00
     without
    0.90
     centra
    0.84
     severe
    0.80
    itando
    0.77
    افی
    0.73
    perm
    0.73
    ワーク
    0.72
    kula
    0.72
     would
    0.71
    Activations Density 0.034%

    No Known Activations