© 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. 115606
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tags

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

    The neuron is highly sensitive to the structural formatting of code blocks—especially long runs of leading spaces (indentation), braces, and other layout tokens in an Ext JS snippet.

    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
     Vigil
    -0.83
    UMENTS
    -0.83
    itern
    -0.81
    galus
    -0.79
    ()<
    -0.79
    Ava
    -0.78
    Mejores
    -0.78
     デイ
    -0.78
    centiles
    -0.77
    ndrome
    -0.76
    POSITIVE LOGITS
     xt
    1.08
     itemId
    0.92
    cls
    0.84
    getText
    0.75
     flex
    0.74
     text
    0.73
     items
    0.72
    text
    0.71
    ulan
    0.71
    handler
    0.70
    Activations Density 0.005%

    No Known Activations