© 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. 65893
    Prev
    Next
    INDEX
    Explanations

    Page Load Event

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

    The neuron fires on structural code identifiers and markup tags—e.g. method‐name tokens like “Page”, “_”, “Load” and XML element names such as “string.”

    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
    えて
    -0.77
    tanaman
    -0.72
    ousy
    -0.72
     Informationen
    -0.71
    GetResponse
    -0.68
    DICT
    -0.68
     eisen
    -0.66
     FLOOD
    -0.66
     afstand
    -0.66
    łop
    -0.66
    POSITIVE LOGITS
    PositiveButton
    0.75
     entrevistas
    0.74
     DAC
    0.73
     IRB
    0.68
     Orville
    0.68
     presenter
    0.68
     Mic
    0.68
     CDS
    0.67
    loader
    0.66
    ​​​​
    0.66
    Activations Density 0.036%

    No Known Activations