© 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. 110692
    Prev
    Next
    INDEX
    Explanations

    inquiring about personal experience

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

    The neuron fires on numeric tokens—i.e. words or symbols representing numbers, quantities, or digits.

    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
    我们
    -1.30
    我們
    -1.27
    ITÉ
    -1.13
    Such
    -1.12
     değildir
    -1.09
    CIÓN
    -1.03
     reacties
    -1.02
     empfiehlt
    -1.02
    畾
    -1.00
    tación
    -1.00
    POSITIVE LOGITS
     because
    1.33
     others
    1.21
     when
    1.20
     !(
    1.16
     other
    1.16
    pho
    1.13
     I
    1.09
     most
    1.05
    りを
    1.00
     Hingga
    0.98
    Activations Density 0.078%

    No Known Activations