© 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. 91289
    Prev
    Next
    INDEX
    Explanations

    Boost Software License

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

    The neuron fires on code‐metadata tokens—library/framework names, module identifiers, and license/header terms (e.g. “fml,” “BOOST,” “LICENSE,” URLs and similar acronyms).

    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
     Alar
    -0.76
    Shortly
    -0.69
     titoli
    -0.68
    Lille
    -0.66
     attraction
    -0.65
     Desember
    -0.65
     mestre
    -0.65
     cabe
    -0.65
     spins
    -0.64
     ALL
    -0.64
    POSITIVE LOGITS
    nji
    0.73
     Bao
    0.72
    distribu
    0.69
    Pause
    0.68
     Drone
    0.67
    Bao
    0.66
    父母
    0.66
    Abc
    0.66
     online
    0.65
     Pause
    0.65
    Activations Density 0.074%

    No Known Activations