© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68198
    Prev
    Next
    INDEX
    Explanations

    JsonProperty, JsonIgnore, DataMember

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

    The neuron activates on code annotations for JSON serialization (e.g. JsonProperty, JsonIgnoreProperties, JsonPropertyName).

    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
    縢
    -1.88
    瞜
    -1.80
    jnych
    -1.65
    ༐
    -1.63
    辚
    -1.62
    
    -1.60
     auffi
    -1.56
    他人
    -1.56
    providedIn
    -1.56
    silueta
    -1.55
    POSITIVE LOGITS
     ”
    1.75
    “
    1.74
    なんですが
    1.70
    b
    1.70
    だったので
    1.69
    を作り
    1.63
     своим
    1.63
     стал
    1.58
     
    1.58
    なのですが
    1.55
    Activations Density 0.001%

    No Known Activations