© 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. 34-GEMMASCOPE-RES-131K
    7. 109416
    Prev
    Next
    INDEX
    Explanations

    Q: followed by questionUS auto tariff

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

    The neuron fires on standalone numeric digits (e.g. individual numbers 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_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
     until
    -0.87
     variar
    -0.87
     Légion
    -0.78
     Vaticano
    -0.77
     svårt
    -0.77
     filtra
    -0.77
    pielen
    -0.75
     rendement
    -0.74
     tuya
    -0.73
     sinto
    -0.73
    POSITIVE LOGITS
     له
    0.90
    ULA
    0.83
    Kenneth
    0.80
    しゅ
    0.77
    ismet
    0.77
     INTERESAR
    0.75
    IES
    0.75
     edema
    0.74
     thousand
    0.74
     PRIM
    0.74
    Activations Density 0.000%

    No Known Activations