© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71904
    Prev
    Next
    INDEX
    Explanations

    programming code and lists

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

    The neuron is activated by code “function(…)” constructs—that is, JavaScript-style function definitions and their parameter list syntax.

    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
     Mě
    -1.06
     клавиа
    -0.98
    гули
    -0.98
    DriverManager
    -0.97
    HasIndex
    -0.95
     jugar
    -0.92
     Př
    -0.91
     silnika
    -0.91
    MutableLiveData
    -0.90
     ایالات
    -0.90
    POSITIVE LOGITS
     schließlich
    1.23
    Passer
    1.09
     troisième
    1.05
     third
    1.01
     quatrième
    0.98
     derde
    0.97
    Clic
    0.96
     lastly
    0.96
     these
    0.94
    Proces
    0.93
    Activations Density 0.018%

    No Known Activations