© 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. 47071
    Prev
    Next
    INDEX
    Explanations

    data structures (Map, Set, HashMap, Dict)

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

    The neuron fires on import or usage of Java collection types (e.g. Map, HashMap, List, Set) in 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
    direct
    -0.80
    anticipated
    -0.79
    tisation
    -0.78
    davis
    -0.78
    Direct
    -0.78
     ubica
    -0.78
     chief
    -0.77
    直接
    -0.76
    avoit
    -0.76
     direct
    -0.76
    POSITIVE LOGITS
     superheroes
    0.89
     Wonders
    0.76
    Tav
    0.76
    Ers
    0.76
    ılır
    0.71
     Santander
    0.71
    新品
    0.69
     Beatles
    0.69
    —¡
    0.69
    HashMap
    0.68
    Activations Density 0.003%

    No Known Activations