© 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. 116526
    Prev
    Next
    INDEX
    Explanations

    numbers and technical language

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

    The neuron specializes in spotting numeric tokens—numbers and digits that convey quantities, measurements, or 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
    🥑
    -0.75
     Româ
    -0.69
    quierda
    -0.68
    ASX
    -0.68
     něm
    -0.68
    zob
    -0.68
     Wiesbaden
    -0.67
     nutmeg
    -0.67
     negó
    -0.67
     platos
    -0.66
    POSITIVE LOGITS
     leading
    0.98
     rays
    0.89
     fin
    0.85
     soft
    0.81
     precursors
    0.74
    簇
    0.73
    haustible
    0.73
    soft
    0.71
     starts
    0.71
     first
    0.71
    Activations Density 0.049%

    No Known Activations