© 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. 82317
    Prev
    Next
    INDEX
    Explanations

    Sir and Dame titles

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

    The neuron primarily picks out numeric tokens (digit sequences).

    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
    хіво
    -0.72
     Seneca
    -0.71
     Abraham
    -0.70
     diye
    -0.68
     ik
    -0.67
     Nord
    -0.66
    ା
    -0.66
    wohner
    -0.66
     Ara
    -0.65
    iguous
    -0.65
    POSITIVE LOGITS
     Sir
    3.36
    Sir
    3.25
     Dame
    2.67
    Dame
    2.59
     CBE
    2.28
     OBE
    2.05
     sir
    2.02
     SIR
    1.95
    SIR
    1.95
     dame
    1.90
    Activations Density 0.105%

    No Known Activations