© 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. 22-GEMMASCOPE-RES-131K
    7. 33512
    Prev
    Next
    INDEX
    Explanations

    php code execution

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

    The neuron activates on PHP’s object‐method operator (`->`)—that is, it detects instances of calling methods or accessing properties on objects.

    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
     in
    -2.17
     all
    -2.11
     with
    -2.06
     only
    -2.05
    くに
    -2.03
    しましたが
    -1.85
     冊
    -1.84
    などが
    -1.82
     just
    -1.79
    ptonshire
    -1.78
    POSITIVE LOGITS
    を行います
    2.41
    </h2>
    2.23
    えっ
    2.23
    をします
    2.19
    にします
    2.17
    殽
    2.13
    のですか
    2.08
    迨
    2.08
    為に
    2.06
    のでしょう
    2.05
    Activations Density 0.005%

    No Known Activations