© 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. 77960
    Prev
    Next
    INDEX
    Explanations

    PHP database functions

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

    The neuron fires on PHP database‐access tokens and SQL keywords, essentially detecting MySQL query and fetch calls in PHP code.

    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
    家電
    -0.92
     télévis
    -0.90
     on
    -0.84
    停止
    -0.82
     with
    -0.82
     With
    -0.79
    ordion
    -0.79
     Grüsse
    -0.79
     französ
    -0.77
    жей
    -0.76
    POSITIVE LOGITS
     verdaderos
    0.96
    OCI
    0.95
     PREVIOUS
    0.91
     OOP
    0.90
    OOP
    0.88
    real
    0.85
     procedimientos
    0.85
    円で
    0.85
     Procedural
    0.85
     HOU
    0.85
    Activations Density 0.004%

    No Known Activations