© 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. 10-GEMMASCOPE-RES-131K
    7. 70687
    Prev
    Next
    INDEX
    Explanations

    gain, acquire, win

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

    This neuron detects the letter sequence “gan” wherever it appears within words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     “
    -2.33
    ed
    -2.14
    ee
    -2.05
    m
    -2.02
    热水
    -2.02
     \"
    -1.96
    “
    -1.96
    zości
    -1.93
     administer
    -1.86
     tempting
    -1.86
    POSITIVE LOGITS
    鵟
    1.83
    了
    1.81
    탓
    1.78
    genodigd
    1.75
     کنه
    1.74
    sibilità
    1.74
    iconductors
    1.73
     清新
    1.72
     コーディネート
    1.70
     necessárias
    1.69
    Activations Density 0.004%

    No Known Activations