© 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. 67297
    Prev
    Next
    INDEX
    Explanations

    '+', '+=' assignments and code

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

    This neuron fires on numeric literals (tokens consisting of digits or containing 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_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
     both
    -0.81
    Ahmad
    -0.79
    ֫
    -0.77
     Blan
    -0.76
    Fract
    -0.75
     inaugural
    -0.74
    翱
    -0.74
     often
    -0.71
     подчер
    -0.71
     sanitarias
    -0.71
    POSITIVE LOGITS
     funciones
    0.84
     jednou
    0.84
     prefixes
    0.83
    🔠
    0.75
     nasz
    0.74
    фора
    0.74
    ではある
    0.73
    lineTo
    0.73
     followed
    0.72
    renia
    0.71
    Activations Density 0.020%

    No Known Activations