© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58645
    Prev
    Next
    INDEX
    Explanations

    keywords for code contexts

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

    This neuron fires on top‐level Ruby “declaration” or DSL lines—import/configuration calls and test definitions (e.g. require, include, describe, version, sha, name, etc.).

    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
    URDAY
    -0.92
    {\"
    -0.88
    も同じ
    -0.88
     Werbung
    -0.84
     prazer
    -0.82
     sobą
    -0.80
    に追加
    -0.80
    火的
    -0.80
     неболь
    -0.80
     Webseiten
    -0.79
    POSITIVE LOGITS
     do
    1.04
    Jaw
    0.86
    اليا
    0.86
    ష్
    0.85
     licences
    0.85
    ȯ
    0.84
     did
    0.82
     ਨਾਲ
    0.81
    ̣i
    0.81
    Did
    0.80
    Activations Density 0.046%

    No Known Activations