© 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. 10-GEMMASCOPE-RES-131K
    7. 69049
    Prev
    Next
    INDEX
    Explanations

    php/template code with binding

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

    This neuron detects server‐side or template code delimiters (e.g. PHP tags like “<?php …?>” or template syntax like “{% … %}” and “{{ … }}”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    l
    -2.11
    t
    -1.98
    s
    -1.82
    1
    -1.80
    r
    -1.80
    n
    -1.75
    f
    -1.70
    k
    -1.68
    c
    -1.61
    la
    -1.48
    POSITIVE LOGITS
    '/',
    1.68
    limiento
    1.57
    ής
    1.52
    thail
    1.49
    のですね
    1.43
    kval
    1.40
     தமி
    1.40
    ſch
    1.40
    plik
    1.39
    yym
    1.39
    Activations Density 0.003%

    No Known Activations