© 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. 40065
    Prev
    Next
    INDEX
    Explanations

    code syntax and documentation keywords

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

    The neuron spots tokens that specify quantitative constraints (counts, bounds, or optionality) in structured schema or API definitions.

    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
    以及
    -1.30
    及び
    -1.23
    および
    -1.11
    なども
    -0.96
     rapist
    -0.93
    以外の
    -0.91
     guangdong
    -0.88
    opie
    -0.85
     alcune
    -0.85
    或者
    -0.84
    POSITIVE LOGITS
     restaurantes
    1.28
     dokument
    1.11
     niños
    1.08
     musique
    1.05
     bienvenue
    1.04
    ⓐ
    1.04
     abar
    1.03
    bitol
    1.00
     salonu
    0.99
     wy
    0.99
    Activations Density 0.002%

    No Known Activations