© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57545
    Prev
    Next
    INDEX
    Explanations

    live, living, and life

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

    references to ".com" websites, live performances, or publications with "live" in their titles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron consistently fires on the string “live” (in various capitalizations), as it appears in titles, names, and URLs.

    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
     daar
    -0.82
    itoire
    -0.79
    zés
    -0.78
     letzt
    -0.78
     tranquility
    -0.77
     ziehen
    -0.76
    rizio
    -0.75
    getText
    -0.75
    مين
    -0.75
     calming
    -0.74
    POSITIVE LOGITS
     sống
    0.93
     live
    0.91
    living
    0.88
    Live
    0.87
     Live
    0.84
     lives
    0.83
    live
    0.82
     lived
    0.82
    Living
    0.73
     discrimin
    0.73
    Activations Density 0.028%

    No Known Activations