© 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. 98675
    Prev
    Next
    INDEX
    Explanations

    Mav Tomcat fighter

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

    The neuron fires on numeral tokens—especially multi‐digit numbers (years, measurements) and numeric sequences—highlighting any digits-based token in the text.

    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
    FieldBuilder
    -0.79
     detective
    -0.78
    ışık
    -0.74
    issor
    -0.71
    muir
    -0.71
    indiri
    -0.70
     chip
    -0.70
     Battery
    -0.69
     poison
    -0.69
     battery
    -0.69
    POSITIVE LOGITS
     Maverick
    1.28
    Mav
    1.06
     fighter
    1.04
    Maverick
    1.03
     Fighter
    0.95
     Tomcat
    0.94
    Fighter
    0.93
     Mav
    0.92
     Mavericks
    0.87
     MiG
    0.86
    Activations Density 0.012%

    No Known Activations