© 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. 36688
    Prev
    Next
    INDEX
    Explanations

    getter method calls

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

    This neuron detects method‐name tokens in code snippets—especially getter or similar function declarations.

    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
    zaSy
    -1.34
    nexpected
    -1.33
    masker
    -1.27
    olympic
    -1.23
    gigabyte
    -1.20
     exceedingly
    -1.20
     sorpresas
    -1.20
    hijab
    -1.20
     malha
    -1.20
     vulgares
    -1.20
    POSITIVE LOGITS
    ()
    1.49
    A
    1.23
     That
    1.15
    </strong>
    1.14
    For
    1.12
    Not
    1.09
    a
    1.09
     (
    1.09
     get
    1.09
    1.08
    Activations Density 0.001%

    No Known Activations