© 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. 34-GEMMASCOPE-RES-131K
    4. 402
    Prev
    Next
    INDEX
    Explanations

    json parsing, Veeva, Characterization, vehicles, Q&A

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

    This neuron flags occurrences of “Json” (and related JSON‐library or serialization identifiers) in source code.

    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
     gaga
    -0.82
     KISS
    -0.82
     urg
    -0.80
     cip
    -0.77
     jars
    -0.77
    insegna
    -0.75
     Quar
    -0.75
    Tuple
    -0.74
     PBT
    -0.74
     jobber
    -0.74
    POSITIVE LOGITS
     Sacramento
    1.34
    Sacramento
    1.12
     California
    0.82
    opin
    0.77
    ándo
    0.71
    California
    0.70
    ignez
    0.70
    ictus
    0.70
     Musiker
    0.68
     what
    0.68
    Activations Density 0.004%

    No Known Activations