© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83705
    Prev
    Next
    INDEX
    Explanations

    function or purpose

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

    The neuron is detecting numeric and quantitative expressions—digits, spelled-out numbers/ordinals, and words indicating quantities.

    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
    volves
    -0.98
    iados
    -0.89
     UnityEngine
    -0.87
     प्रयास
    -0.87
    hadapi
    -0.86
    ڼ
    -0.84
    anguage
    -0.83
    ﺸ
    -0.83
    ícias
    -0.83
    Примеры
    -0.81
    POSITIVE LOGITS
     function
    5.56
     purpose
    5.03
     functions
    4.50
    function
    4.19
     Function
    3.67
     purposes
    3.61
     función
    3.58
     funzione
    3.56
    Function
    3.56
     role
    3.48
    Activations Density 0.249%

    No Known Activations