© 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. 34-GEMMASCOPE-RES-131K
    7. 6708
    Prev
    Next
    INDEX
    Explanations

    JSON structured lists

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

    The neuron strongly activates on the commas that separate fields and values in JSON‐like data structures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     supremely
    -1.20
     for
    -1.18
     or
    -1.16
     ostensibly
    -1.16
     because
    -1.12
     especially
    -1.12
     to
    -1.11
     from
    -1.09
     if
    -1.09
     overtly
    -1.08
    POSITIVE LOGITS
     "
    1.73
     “
    1.45
    seems
    1.19
     "@
    1.17
    )+"
    1.16
     остальные
    1.15
     "_
    1.13
     carrière
    1.12
    started
    1.11
     atteindre
    1.11
    Activations Density 0.041%

    No Known Activations