© 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. 22-GEMMASCOPE-RES-131K
    7. 84410
    Prev
    Next
    INDEX
    Explanations

    github.com, gmail.com, apache.commons, Lin Po, East Falmouth

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

    This neuron fires on tokens that are parts of code import paths—particularly domain names and repository segments (e.g. “github.com/…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    glPushMatrix
    -1.11
     फिल्म
    -1.07
     Mr
    -1.05
     memorable
    -1.05
    但这
    -1.04
    ׄ
    -1.04
    但他
    -1.03
     Pump
    -1.03
     overwhelmingly
    -1.02
     today
    -1.01
    POSITIVE LOGITS
    Même
    1.28
     Brasilien
    1.20
    },
    1.13
     отредакти
    1.12
     сериал
    1.09
    蜻
    1.06
     berita
    1.03
    Когда
    1.03
     нам
    1.02
    ૨
    1.02
    Activations Density 0.001%

    No Known Activations