© 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. 67766
    Prev
    Next
    INDEX
    Explanations

    pronounced atrophy

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

    The neuron detects numeric tokens or numerical measurements (including integers and decimals).

    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
    ľa
    -0.85
    ابط
    -0.85
     verheir
    -0.83
     With
    -0.82
     gezicht
    -0.81
    prakti
    -0.81
     firstly
    -0.80
    zydent
    -0.78
     dejar
    -0.78
     Along
    -0.77
    POSITIVE LOGITS
    despite
    1.03
    QUÉ
    0.97
     bono
    0.92
     bygger
    0.92
     behe
    0.92
    icular
    0.90
     COLE
    0.89
     malnutrition
    0.88
    ępu
    0.88
     antonio
    0.88
    Activations Density 0.048%

    No Known Activations