© 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. 65398
    Prev
    Next
    INDEX
    Explanations

    erb templating tags

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

    The neuron fires on technical phrases naming Rails’ Form Helper and its object‐attribute usage, i.e. when the text refers to Rails form builder methods and attributes.

    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
     flavored
    -0.77
    restre
    -0.72
     Kugel
    -0.71
    樣的
    -0.71
     levantó
    -0.70
     loadData
    -0.69
    صیلات
    -0.69
    hore
    -0.68
     Romagna
    -0.67
    后再
    -0.66
    POSITIVE LOGITS
     link
    0.92
    collection
    0.86
    concat
    0.84
    FormBuilder
    0.84
     池
    0.82
     dość
    0.81
     afstand
    0.81
    selectAll
    0.79
     bağlant
    0.79
     builders
    0.77
    Activations Density 0.067%

    No Known Activations