© 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. 35721
    Prev
    Next
    INDEX
    Explanations

    computing infrastructure and code

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

    This neuron activates on code identifiers that are names of types or resource objects (i.e. capitalized type/class names).

    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
    rā
    -1.25
    collo
    -1.07
    nasium
    -1.07
    блиоте
    -1.03
    ooooooo
    -0.98
     mūsų
    -0.98
    $?
    -0.96
     mutiara
    -0.96
    attendre
    -0.96
    hark
    -0.96
    POSITIVE LOGITS
     Agric
    1.06
    同学
    1.02
    ған
    0.96
    ০
    0.95
    你的
    0.95
     affidavits
    0.93
     подойдет
    0.88
    ၀
    0.85
    illots
    0.85
     πάν
    0.84
    Activations Density 0.003%

    No Known Activations