© 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. 34-GEMMASCOPE-RES-131K
    7. 56096
    Prev
    Next
    INDEX
    Explanations

    programming interfaces and keywords

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

    This neuron strongly activates on tokens containing numerical digits (i.e. numeric literals or identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     lju
    -0.75
     purchases
    -0.73
     Eust
    -0.71
    Kud
    -0.69
     Stans
    -0.67
    建築
    -0.66
    ibrill
    -0.64
     Rosario
    -0.64
    Basketball
    -0.63
    kih
    -0.63
    POSITIVE LOGITS
     degraded
    0.73
    mekte
    0.69
     hyperplasia
    0.67
    pañas
    0.65
    nino
    0.64
     сумму
    0.63
    ampe
    0.61
    を見せて
    0.61
    名の
    0.61
     IMDb
    0.60
    Activations Density 0.058%

    No Known Activations