© 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. 130792
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on references to the current object instance (e.g. “this” in JavaScript or “self” in Python).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    `this` or `self` access

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     parfü
    -1.47
     triko
    -1.34
     biela
    -1.27
    archivi
    -1.24
     univerz
    -1.23
     telefonu
    -1.23
     incroy
    -1.22
    引用元
    -1.20
     salonu
    -1.19
    här
    -1.19
    POSITIVE LOGITS
     also
    2.20
     is
    1.44
    u
    1.31
    e
    1.21
     a
    1.20
    には
    1.20
    is
    1.20
    ur
    1.19
    o
    1.16
    ist
    1.14
    Activations Density 0.003%

    No Known Activations