© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 80000
    Prev
    Next
    INDEX
    Explanations

    add, delegate, save, bindValue, setParameter

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

    The neuron is keying on object‐oriented method calls (identifying tokens involved in “object.method(…)” invocation patterns).

    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
    alucía
    -1.02
     照明
    -1.00
     onu
    -0.97
    щены
    -0.96
    ренко
    -0.96
    apé
    -0.94
    lierung
    -0.93
    bling
    -0.90
    怯
    -0.88
    urally
    -0.88
    POSITIVE LOGITS
     also
    2.36
     then
    1.47
     также
    1.36
    Zdrav
    1.21
     також
    1.18
     همچنین
    1.16
    Также
    1.13
     także
    1.09
     أيضًا
    1.09
     også
    1.07
    Activations Density 0.003%

    No Known Activations