© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27495
    Prev
    Next
    INDEX
    Explanations

    payment addresses and teams

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

    This neuron fires on numeric tokens—i.e. it detects number literals (integers and decimals) in the text.

    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
     віта
    -1.01
     tanti
    -0.97
    Esse
    -0.91
    日常
    -0.90
    有一些
    -0.89
    虽然
    -0.88
    Maak
    -0.88
    "))
    -0.88
     スニーカー
    -0.88
     tinha
    -0.88
    POSITIVE LOGITS
     declaración
    1.02
    だそうです
    1.02
    ೦
    1.01
    嘖
    0.95
     of
    0.95
    ()
    0.95
    わせて
    0.95
     negociación
    0.94
    ATIVA
    0.93
     будете
    0.92
    Activations Density 0.082%

    No Known Activations