© 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. 28107
    Prev
    Next
    INDEX
    Explanations

    Audacity and Daily Pilot

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

    The neuron responds to isolated numeric tokens (digits or 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_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
    urlencoded
    -1.07
    angal
    -0.94
    mathcal
    -0.93
     động
    -0.91
     Custom
    -0.89
     Poly
    -0.88
     fortsätter
    -0.87
     dAtA
    -0.87
    parc
    -0.87
    𝐪
    -0.86
    POSITIVE LOGITS
     秋冬
    1.14
     BORROW
    1.02
     padi
    1.01
    她们
    0.98
    Tarifs
    0.95
    Rozmiar
    0.93
     vettor
    0.93
     Bahan
    0.91
     saus
    0.91
    rousel
    0.91
    Activations Density 0.000%

    No Known Activations