© 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. 45487
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured text

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

    The neuron fires on tokens characteristic of technical documentation or code/web assets—things like “stylesheet,” “release,” “.com” URLs, HTTP status codes, and similar software‐oriented jargon.

    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
    INCLUDE
    -0.81
    yta
    -0.76
     ويكي
    -0.75
     démocratique
    -0.72
     Projekte
    -0.72
     Sites
    -0.71
     aparat
    -0.71
     ác
    -0.71
    ikiki
    -0.69
    よく
    -0.69
    POSITIVE LOGITS
     kenne
    0.69
    `
    0.69
    land
    0.68
     Movie
    0.67
    链接
    0.66
     PASSWORD
    0.65
    stron
    0.65
    Dependency
    0.63
    вление
    0.62
    dor
    0.62
    Activations Density 0.041%

    No Known Activations