© 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. 1859
    Prev
    Next
    INDEX
    Explanations

    web client-server applications

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

    The neuron fires on technical software‐architecture jargon and hyphenated compound terms (e.g. middleware, mid-1990s, three-tiered, client-server, multi-tiered, state-of-the-art).

    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
    ﺎ
    -0.85
    diging
    -0.82
    Datepicker
    -0.79
    CMake
    -0.77
    therners
    -0.77
    فی
    -0.76
    творення
    -0.75
     Espagne
    -0.75
    hellip
    -0.74
    EU
    -0.73
    POSITIVE LOGITS
     web
    1.95
     Web
    1.70
     client
    1.63
    web
    1.47
    Web
    1.45
     WEB
    1.27
     Client
    1.26
    client
    1.20
     웹
    1.19
     application
    1.14
    Activations Density 0.287%

    No Known Activations