© 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. 22-GEMMASCOPE-RES-131K
    7. 9561
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron primarily detects numeric quantity expressions (digits, fractions, and measurement units) as found in conversion or arithmetic questions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Wikipédia
    -1.05
     skå
    -1.04
    isait
    -0.95
     matel
    -0.91
     ECONOMICS
    -0.91
     complexe
    -0.90
    ḏ
    -0.88
     signes
    -0.88
    Merhaba
    -0.86
     tempi
    -0.86
    POSITIVE LOGITS
    usura
    0.99
    ή
    0.95
     to
    0.93
    ੍ਹ
    0.92
    Література
    0.91
     одежда
    0.91
    offsetHeight
    0.90
    arons
    0.89
    Además
    0.88
     передний
    0.87
    Activations Density 0.009%

    No Known Activations