© 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. 39998
    Prev
    Next
    INDEX
    Explanations

    different languages and contexts

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

    The neuron activates on standalone numeric tokens (e.g. version numbers, line numbers, or other number strings).

    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
    requestData
    -0.92
     Laufe
    -0.92
    тых
    -0.89
    ukų
    -0.85
     امکان
    -0.84
     or
    -0.83
    Notation
    -0.83
     while
    -0.82
     tertawa
    -0.82
    當初
    -0.82
    POSITIVE LOGITS
    opies
    1.07
    Maß
    1.05
    おわりに
    1.03
    arrête
    1.02
    ַל
    1.00
     bahagian
    1.00
    ridescent
    0.97
     kunjungan
    0.96
     например
    0.95
     piese
    0.95
    Activations Density 0.000%

    No Known Activations