© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35633
    Prev
    Next
    INDEX
    Explanations

    web framework components

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

    The neuron fires on occurrences of programming‐library or framework identifiers (e.g. Razor, Django shortcuts, Flask HttpResponse, Angular template, PHP Magento classes, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     from
    -1.51
    EN
    -1.25
    J
    -1.13
     so
    -1.13
    S
    -1.11
    0
    -1.11
    al
    -1.08
    L
    -1.07
    D
    -1.07
     an
    -1.06
    POSITIVE LOGITS
     تجمعات
    1.20
    rét
    1.20
    SNOW
    1.19
    seamnă
    1.16
     SNOW
    1.16
    cestors
    1.15
    IActionResult
    1.14
    Afri
    1.13
    Filmography
    1.10
    Politique
    1.08
    Activations Density 0.003%

    No Known Activations