© 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. 36501
    Prev
    Next
    INDEX
    Explanations

    name identifier

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

    This neuron detects occurrences of the identifier or field name “name” in code or data.

    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
     for
    -1.45
     on
    -1.38
     would
    -1.27
     /
    -1.27
    ↵↵
    -1.26
     might
    -1.22
    g
    -1.20
    it
    -1.20
     may
    -1.20
     just
    -1.19
    POSITIVE LOGITS
     personnaliser
    1.29
     Татьяна
    1.26
    karena
    1.26
     véritable
    1.25
     kaksi
    1.23
     ſon
    1.23
    同樣
    1.20
     spannende
    1.17
    тут
    1.17
    brilliant
    1.17
    Activations Density 0.018%

    No Known Activations