© 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. 34-GEMMASCOPE-RES-131K
    7. 75699
    Prev
    Next
    INDEX
    Explanations

    contributors and licenses

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

    The neuron fires on occurrences of Django (and related) module import paths in 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
    ülerin
    -0.87
    电视台
    -0.87
     variable
    -0.87
     larger
    -0.87
    enovo
    -0.85
     práce
    -0.84
     koncep
    -0.83
    vádz
    -0.83
     відео
    -0.82
    fromDate
    -0.82
    POSITIVE LOGITS
    auth
    1.02
     auth
    0.93
    Où
    0.85
     mache
    0.85
    shine
    0.84
    ejemplo
    0.82
     griega
    0.82
    enabled
    0.79
     Ста
    0.78
     Ejemplo
    0.76
    Activations Density 0.004%

    No Known Activations