© 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. 34-GEMMASCOPE-RES-131K
    4. 91182
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    The neuron strongly activates on standalone numeric tokens (e.g. years, counts, page 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_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
     Some
    -0.83
    ائج
    -0.82
     Only
    -0.81
     ONLY
    -0.80
     jota
    -0.75
     only
    -0.75
     слов
    -0.74
    zen
    -0.73
     first
    -0.73
     More
    -0.73
    POSITIVE LOGITS
     daleko
    0.98
    unser
    0.91
     cielos
    0.87
     рынке
    0.85
     geniales
    0.85
    Spenden
    0.85
     AHEAD
    0.85
    ürze
    0.84
     marquer
    0.84
    hre
    0.83
    Activations Density 0.000%

    No Known Activations