© 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. 103662
    Prev
    Next
    INDEX
    Explanations

    Leipzig

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

    The neuron activates primarily on numeric tokens—e.g. years, street numbers, postal codes, and other digit 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
    웡
    -0.77
    RSC
    -0.76
    WSGI
    -0.76
    Decline
    -0.74
     Illuminated
    -0.73
    Twilight
    -0.73
    Strongly
    -0.72
     réfugiés
    -0.71
     Aru
    -0.71
    unjukkan
    -0.71
    POSITIVE LOGITS
     Leipzig
    0.87
     бъдат
    0.77
    alloc
    0.76
    ifiers
    0.74
    Vertical
    0.74
    onavirus
    0.73
     coronavirus
    0.73
    空格
    0.73
    Config
    0.72
    VERTICAL
    0.72
    Activations Density 0.020%

    No Known Activations