© 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. 13209
    Prev
    Next
    INDEX
    Explanations

    code declarations and assignments

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

    This neuron fires on code tokens related to file‐handling (e.g. references to file variables and output stream classes).

    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
    HAHAHA
    -1.05
    ᴜ
    -1.04
    johtaja
    -1.03
     koš
    -1.02
     fön
    -1.00
    HAHAHAHA
    -1.00
    pense
    -0.99
    HAHA
    -0.98
     taba
    -0.98
    ProcessEvent
    -0.96
    POSITIVE LOGITS
     by
    1.02
     in
    0.99
     quests
    0.96
     Sup
    0.91
     on
    0.91
    1
    0.90
     not
    0.87
    0
    0.84
     Love
    0.83
     Friends
    0.83
    Activations Density 0.006%

    No Known Activations