© 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. 103951
    Prev
    Next
    INDEX
    Explanations

    meg- words

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

    This neuron activates on the substring “meg,” i.e. words containing the prefix “mega.”

    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
     zwanzig
    -2.66
     所有
    -2.66
     két
    -2.58
     -
    -2.55
     тысячи
    -2.27
     anfangs
    -2.19
     quell
    -2.17
     excell
    -2.16
     pivotal
    -2.14
     but
    -2.11
    POSITIVE LOGITS
    Several
    2.84
    Surprisingly
    2.83
    蹓
    2.77
    Despite
    2.75
    Many
    2.73
    Some
    2.72
    綃
    2.66
    Because
    2.64
     休閒
    2.63
    Almost
    2.58
    Activations Density 0.001%

    No Known Activations