© 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. 57564
    Prev
    Next
    INDEX
    Explanations

    legal documents

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

    The neuron fires on standalone numeric tokens (integers or decimals), effectively detecting 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_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
     out
    -1.81
    Also
    -1.70
    s
    -1.67
     unrelenting
    -1.65
    Many
    -1.65
     facilitating
    -1.63
     bolster
    -1.62
     ensures
    -1.61
    Since
    -1.59
     meticulous
    -1.59
    POSITIVE LOGITS
    螃
    1.99
    亹
    1.84
     différents
    1.81
    是要
    1.73
    苼
    1.66
     VERY
    1.65
     REALLY
    1.64
    部分が
    1.63
    킁
    1.63
    に入れる
    1.60
    Activations Density 0.016%

    No Known Activations