© 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. 75116
    Prev
    Next
    INDEX
    Explanations

    `<?php` or `// RUN:` or `Sunflat` or `Downsizing`

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

    The neuron fires on numeric tokens—that is, on sequences of digits (including integers, floats, coordinates, and other numbers).

    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
    ！(
    -1.21
    ۹
    -1.13
    撓
    -1.06
    ！！
    -1.03
     viewWillAppear
    -1.02
    >
    -1.02
    Комментарии
    -1.02
     occupa
    -0.98
    ！！！
    -0.97
    makeatother
    -0.97
    POSITIVE LOGITS
     doigt
    1.03
    र्व
    0.98
    Drying
    0.98
     cercana
    0.97
     seuil
    0.97
    bolsa
    0.96
    parag
    0.96
     mencionado
    0.96
     hervorragend
    0.95
     ibland
    0.94
    Activations Density 0.001%

    No Known Activations