© 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. 76535
    Prev
    Next
    INDEX
    Explanations

    Super secure

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

    This neuron detects PHP namespace and class path tokens (particularly the backslash separators and names in Drupal’s namespaced class definitions).

    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
    Geograf
    -0.81
    muo
    -0.77
     Stakes
    -0.72
    unuz
    -0.71
     fuk
    -0.70
    beve
    -0.69
     Manns
    -0.68
    maq
    -0.68
     starting
    -0.66
    anca
    -0.66
    POSITIVE LOGITS
     Drupal
    0.83
     tə
    0.78
     CHAMP
    0.78
     владе
    0.77
     zamanda
    0.76
     Euphrates
    0.76
    enschein
    0.75
    Drupal
    0.75
     Pha
    0.75
     Snap
    0.73
    Activations Density 0.024%

    No Known Activations