© 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. 50230
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    This neuron responds to unusually long numeric tokens (multi-digit 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
    一百
    -1.07
    надцать
    -0.97
     hundred
    -0.94
     LXXX
    -0.90
     Hundred
    -0.85
     Ninety
    -0.84
    ١
    -0.84
    ⲓ
    -0.84
     ninety
    -0.82
     tenth
    -0.81
    POSITIVE LOGITS
     forty
    1.77
    4
    1.69
    3
    1.60
     Forty
    1.55
     thirty
    1.52
     ۴
    1.48
     Thirty
    1.42
    Thirty
    1.41
    四十
    1.36
    Forty
    1.33
    Activations Density 0.079%

    No Known Activations