© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102674
    Prev
    Next
    INDEX
    Explanations

    names starting with G

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

    The neuron strongly activates on tokens beginning with the uppercase letter “G,” especially proper names.

    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
     G
    -1.01
    G
    -0.79
     gaf
    -0.75
     Getter
    -0.75
     g
    -0.75
     Weasley
    -0.75
     గ
    -0.73
    льні
    -0.73
     نہیں
    -0.71
     partielle
    -0.69
    POSITIVE LOGITS
    Тип
    0.78
    caid
    0.76
    女孩子
    0.75
    пион
    0.74
    dbh
    0.73
     Arbitrary
    0.73
     Continuing
    0.73
    TPL
    0.72
     JPMorgan
    0.72
    αρα
    0.72
    Activations Density 0.049%

    No Known Activations