© 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. 10-GEMMASCOPE-RES-131K
    4. 110610
    Prev
    Next
    INDEX
    Explanations

    def up or change

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

    This neuron fires on programming code syntax—particularly definitions of database migrations (e.g. “ActiveRecord::Migration[…]”, “def up”, import/export statements, 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_10/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
     artikke
    -1.36
    儛
    -1.36
    ...");
    
    -1.36
     arvio
    -1.30
     esimer
    -1.29
     this
    -1.29
     cumplido
    -1.27
     sagde
    -1.25
     both
    -1.23
     båda
    -1.23
    POSITIVE LOGITS
    ⅽ
    1.27
     done
    1.27
     again
    1.22
     instead
    1.21
     чтобы
    1.20
    𝐥
    1.19
     próxima
    1.18
     hopefully
    1.16
    again
    1.13
     pokud
    1.13
    Activations Density 0.045%

    No Known Activations