© 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. 25631
    Prev
    Next
    INDEX
    Explanations

    Full Version

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find HTML element 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_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
    atangan
    -0.78
    encontra
    -0.77
    IATION
    -0.77
     Mukherjee
    -0.71
     time
    -0.71
     establish
    -0.71
    woł
    -0.71
     Relationship
    -0.70
     often
    -0.70
     others
    -0.69
    POSITIVE LOGITS
    anama
    0.87
    Namara
    0.85
     Gand
    0.81
     HOOK
    0.81
    ucie
    0.81
    rase
    0.81
     Outsourcing
    0.80
    דה
    0.78
    :"",
    0.78
     locales
    0.78
    Activations Density 0.000%

    No Known Activations