© 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. 71381
    Prev
    Next
    INDEX
    Explanations

    importance and recognition

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

    The neuron activates on numeric tokens and statistical figures (e.g. numbers with or without decimals), effectively detecting quantitative measurements or statistics 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
     or
    -1.09
     âme
    -0.97
     endforeach
    -0.96
     Entrega
    -0.95
     but
    -0.94
    Ако
    -0.91
    complished
    -0.91
     PackageManager
    -0.91
     crossorigin
    -0.89
     kuah
    -0.88
    POSITIVE LOGITS
     importance
    1.48
     it
    1.42
     importância
    1.35
     recognition
    1.22
     priority
    1.12
     reconhe
    1.10
     treated
    1.09
     inclusion
    1.09
     funding
    1.07
     الاعت
    1.07
    Activations Density 0.044%

    No Known Activations