© 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. 35546
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron is detecting numeric literals (including integers and decimals) in code or style sheets.

    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
     egyéb
    -0.89
    自动
    -0.82
     extérieure
    -0.82
    が残
    -0.81
    veni
    -0.81
     siihen
    -0.78
     alábbi
    -0.77
     associées
    -0.76
    Élet
    -0.76
    了自己
    -0.75
    POSITIVE LOGITS
     garner
    0.95
     watu
    0.91
    ('/:
    0.88
    miesz
    0.87
     '+':
    0.82
     MATHEMATICAL
    0.82
    ]()
    0.81
    🫡
    0.79
     Rosalind
    0.78
    繩
    0.78
    Activations Density 0.060%

    No Known Activations