© 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. 10-GEMMASCOPE-RES-131K
    7. 65103
    Prev
    Next
    INDEX
    Explanations

    priority

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

    The neuron is triggered by numeric tokens (especially measurements or statistics), i.e. numbers 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_10/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
     BUT
    -1.98
     definitiva
    -1.78
     frecuentemente
    -1.74
    edoria
    -1.68
    %"),
    -1.67
     ampliamente
    -1.63
    もちゃ
    -1.63
    甯
    -1.61
     nuestras
    -1.61
    ionali
    -1.59
    POSITIVE LOGITS
    as
    1.90
    ）
    1.63
    tably
    1.62
    が上が
    1.61
    ine
    1.59
    ſſen
    1.56
    дний
    1.52
     堆
    1.51
    の高い
    1.49
     beiden
    1.48
    Activations Density 0.017%

    No Known Activations