© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107146
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron fires on CommonJS require statements, especially the module-name string literals passed to require().

    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
     angus
    -0.83
    탁
    -0.81
     constituye
    -0.76
    adec
    -0.75
     adquirir
    -0.73
     comenzar
    -0.72
    riba
    -0.72
     perquè
    -0.72
     separated
    -0.71
     després
    -0.71
    POSITIVE LOGITS
     ہیں
    0.88
     milj
    0.88
     bruges
    0.87
     pris
    0.84
     probleem
    0.83
     SOM
    0.81
     alarme
    0.80
    TextEdit
    0.79
     богат
    0.78
     Mitarbeiter
    0.76
    Activations Density 0.027%

    No Known Activations