© 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. 34-GEMMASCOPE-RES-131K
    4. 65377
    Prev
    Next
    INDEX
    Explanations

    PHP variables, echo, and control flow

    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
     divertir
    -0.87
     kotlinx
    -0.84
     calma
    -0.82
     arché
    -0.82
     Exteriores
    -0.82
     tuyển
    -0.81
     ponga
    -0.79
     Komun
    -0.79
     будин
    -0.79
     Pilih
    -0.79
    POSITIVE LOGITS
     PHP
    1.71
    PHP
    1.52
     isset
    1.47
     $
    1.45
     PDO
    1.41
     $_
    1.30
     php
    1.29
    echo
    1.29
    php
    1.28
    ($
    1.27
    Activations Density 0.491%

    No Known Activations