© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62507
    Prev
    Next
    INDEX
    Explanations

    POST request bodies

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

    The neuron is triggered by programming‐language tokens (annotations, keywords, type names, generics brackets, etc.), i.e. it flags bits of code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Legislature
    -0.77
     केवल
    -0.76
    luiting
    -0.75
     neighbourhood
    -0.74
    LocationManager
    -0.74
    Though
    -0.74
     why
    -0.74
     excludes
    -0.73
     kolory
    -0.73
    儡
    -0.73
    POSITIVE LOGITS
    HashMap
    1.67
     HashMap
    1.58
    JSONObject
    1.31
    NSDictionary
    1.30
    LinkedHashMap
    1.26
    ArrayList
    1.23
     List
    1.22
     Map
    1.21
     ArrayList
    1.16
     JSONObject
    1.16
    Activations Density 0.019%

    No Known Activations