© 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. 73614
    Prev
    Next
    INDEX
    Explanations

    Overflow Bugs Version AZ icon exports

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

    This neuron detects ES6 Reflect API method names (e.g. Reflect.apply, Reflect.construct, Reflect.defineProperty, Reflect.deleteProperty, etc.).

    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
     not
    -2.28
     by
    -1.91
     so
    -1.73
     get
    -1.70
     if
    -1.69
     all
    -1.59
     without
    -1.59
     in
    -1.55
     as
    -1.55
     over
    -1.55
    POSITIVE LOGITS
     trám
    1.84
     empê
    1.60
    為に
    1.53
     centaines
    1.49
     geprüft
    1.48
    ః
    1.46
     trabalho
    1.45
     témo
    1.44
     gänzlich
    1.43
     dénon
    1.38
    Activations Density 0.009%

    No Known Activations