© 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. 82574
    Prev
    Next
    INDEX
    Explanations

    favorite posts and articles

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

    This neuron activates on code-snippet tokens—import/class declarations, identifiers, file names, and numeric literals—i.e. it detects programming or code contexts.

    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
    categorias
    -0.89
    𝜕
    -0.86
    consumo
    -0.82
    fortnite
    -0.82
    travail
    -0.81
    kategori
    -0.79
    бые
    -0.79
    キュリティ
    -0.78
    tinyurl
    -0.77
     從
    -0.76
    POSITIVE LOGITS
     posts
    2.59
     article
    2.22
     articles
    2.14
    posts
    2.03
     Posts
    1.84
     blog
    1.80
    article
    1.78
    Posts
    1.75
    articles
    1.60
     Articles
    1.49
    Activations Density 0.153%

    No Known Activations