© 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. 28372
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

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

    The neuron activates on standalone numeric digits or sequences of digits (i.e. 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
     vaping
    -1.01
     alkot
    -0.96
     recomiendo
    -0.93
    amerikanischer
    -0.93
     Medieval
    -0.86
    ],[
    -0.86
    かり
    -0.84
    ución
    -0.83
     ২০১
    -0.83
    까
    -0.83
    POSITIVE LOGITS
    ícias
    1.07
    Especific
    1.04
    蛱
    1.00
    Planta
    0.94
    geddon
    0.91
     queste
    0.91
    Eerste
    0.91
     solidari
    0.90
    Medidas
    0.90
     manteiga
    0.89
    Activations Density 0.000%

    No Known Activations