© 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. 28530
    Prev
    Next
    INDEX
    Explanations

    `single late` / `during the` context

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

    The neuron strongly activates on numeric tokens (literal numbers, measurements, counts, etc.).

    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
    EMY
    -1.00
     grotte
    -0.92
     balik
    -0.92
    😆
    -0.90
     laki
    -0.90
     samma
    -0.87
     milliard
    -0.87
     kopi
    -0.87
    𐄁
    -0.86
     Sic
    -0.84
    POSITIVE LOGITS
     anybody
    0.88
     it
    0.84
     applied
    0.82
    direccion
    0.81
     whoever
    0.80
     gasped
    0.79
    行った
    0.78
     specifically
    0.76
     chào
    0.76
    ('#
    0.75
    Activations Density 0.185%

    No Known Activations