© 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. 60317
    Prev
    Next
    INDEX
    Explanations

    software quality assurance

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

    The neuron strongly activates on occurrences of the word “software” and closely related software‐engineering terminology in technical or academic 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
     Poitiers
    -0.87
    sisting
    -0.83
     Trafficking
    -0.81
    ariat
    -0.79
    🍾
    -0.77
     DIRECTOR
    -0.77
     animali
    -0.77
    uchter
    -0.77
    translator
    -0.75
     Waterhouse
    -0.75
    POSITIVE LOGITS
    Threats
    1.09
     smells
    1.09
    RQ
    1.03
     smell
    0.99
     refactor
    0.98
     developers
    0.93
     buggy
    0.93
     ref
    0.93
     mined
    0.91
     smelled
    0.89
    Activations Density 0.031%

    No Known Activations