© 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. 60469
    Prev
    Next
    INDEX
    Explanations

    PHP docblock headers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     both
    -0.97
     preciosa
    -0.90
    enservice
    -0.90
     between
    -0.86
    ridgeshire
    -0.85
    رخ
    -0.82
     martie
    -0.81
    tentu
    -0.81
     piani
    -0.80
     kesi
    -0.78
    POSITIVE LOGITS
     PHP
    1.23
    PHP
    1.14
     php
    1.13
    php
    0.99
     Composer
    0.92
    Php
    0.91
     mysqli
    0.85
     astronom
    0.85
     PHPUnit
    0.85
     görmek
    0.85
    Activations Density 0.045%

    No Known Activations