© 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. 38259
    Prev
    Next
    INDEX
    Explanations

    numbers and addresses

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

    The neuron fires on multi-digit numeric tokens (i.e. long integer sequences).

    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
     spoil
    -0.92
     měl
    -0.83
    franc
    -0.81
     sock
    -0.79
    chuga
    -0.77
    ChatMessage
    -0.77
    Framed
    -0.77
    ynthia
    -0.76
    knię
    -0.76
    doise
    -0.75
    POSITIVE LOGITS
     parem
    0.76
    🌦
    0.76
     infections
    0.76
     ŝ
    0.75
     davor
    0.75
     Aruba
    0.74
    🌤
    0.74
     UNAM
    0.73
    ář
    0.72
    值的
    0.72
    Activations Density 0.068%

    No Known Activations