© 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. 72815
    Prev
    Next
    INDEX
    Explanations

    Drupal entity loading

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

    This neuron detects PHP namespace and class references (i.e. tokens in Drupal’s backslash-delimited namespace or class names).

    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
     such
    -2.11
     таких
    -1.81
     SUCH
    -1.63
     såsom
    -1.63
    Such
    -1.55
     Such
    -1.54
    such
    -1.53
     två
    -1.43
     takich
    -1.39
     такой
    -1.37
    POSITIVE LOGITS
     before
    1.35
     mereka
    1.22
     isn
    1.20
     has
    1.17
     as
    1.17
     doesn
    1.16
    ？」
    1.16
    án
    1.16
     goes
    1.16
     makes
    1.16
    Activations Density 0.052%

    No Known Activations