© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35251
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in lists

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

    The neuron consistently activates on numeric tokens (integers or decimals).

    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
     what
    -0.96
     harap
    -0.90
    ♈
    -0.86
    Trichloroethane
    -0.85
    🔧
    -0.84
    ๒
    -0.84
     musique
    -0.83
    Usually
    -0.82
    what
    -0.82
    GaAs
    -0.82
    POSITIVE LOGITS
     keines
    0.85
    哋
    0.81
     nyingi
    0.80
    快速的
    0.78
     bezüglich
    0.78
    落ちる
    0.77
     evtl
    0.77
     попы
    0.77
     urč
    0.76
    ouage
    0.74
    Activations Density 0.081%

    No Known Activations