© 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. 10-GEMMASCOPE-RES-131K
    7. 42549
    Prev
    Next
    INDEX
    Explanations

    setting methods in code

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

    The neuron fires on the verb “set” in code, i.e. when a setter method name begins with “set.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     caratteristiche
    -1.66
     about
    -1.66
     who
    -1.63
     whom
    -1.63
     they
    -1.63
    こない
    -1.61
     THEIR
    -1.58
     Their
    -1.58
     of
    -1.51
    一抹
    -1.41
    POSITIVE LOGITS
    '
    1.62
    īgi
    1.53
    ichtete
    1.50
    法則
    1.50
     tricky
    1.48
     cintur
    1.45
    (
    1.42
     especies
    1.40
     hojas
    1.38
    Comparison
    1.37
    Activations Density 0.005%

    No Known Activations