© 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. 54031
    Prev
    Next
    INDEX
    Explanations

    Q: code or math

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

    The neuron fires on occurrences of the cosine function (e.g. “cos(…)”) in mathematical expressions.

    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
     opportunità
    -0.92
    无法
    -0.92
    Nevertheless
    -0.91
    Yet
    -0.88
     scrittura
    -0.87
    cestry
    -0.85
     někter
    -0.85
    rittura
    -0.85
    avelmente
    -0.85
    Pranala
    -0.85
    POSITIVE LOGITS
    BarButtonItem
    1.05
     kellett
    1.00
     például
    0.98
     senderismo
    0.97
     sinds
    0.94
     doigt
    0.92
     décret
    0.91
    🏳
    0.91
    ícias
    0.91
    曖昧さ回避
    0.90
    Activations Density 0.003%

    No Known Activations