© 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. 57104
    Prev
    Next
    INDEX
    Explanations

    XML, code, or configuration data

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

    This neuron detects document‐ or module‐level declarations (XML prologs/namespaces, YAML front-matter markers, import/use/include statements).

    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
     herramientas
    -0.91
    dign
    -0.91
     conséquences
    -0.87
    Graeme
    -0.86
     quedo
    -0.86
    Chapitre
    -0.83
    Usb
    -0.83
    xem
    -0.82
    enjoy
    -0.82
    Voilà
    -0.82
    POSITIVE LOGITS
     similarly
    0.91
     will
    0.91
     می‌گوید
    0.91
     likewise
    0.88
     also
    0.88
     itself
    0.84
    ουν
    0.84
     Au
    0.83
     Sha
    0.82
    ENGTH
    0.82
    Activations Density 0.108%

    No Known Activations