© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26059
    Prev
    Next
    INDEX
    Explanations

    java data structures

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

    The neuron fires on occurrences of Java collection class names (e.g. List, Map, Set, Arrays) in 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_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
    hush
    -1.05
     hohem
    -1.04
     smrti
    -1.02
    cigarette
    -1.00
     suspensão
    -1.00
    OVERVIEW
    -1.00
     mariposas
    -0.99
    齎
    -0.98
     personagens
    -0.98
     rutas
    -0.98
    POSITIVE LOGITS
     when
    1.09
     of
    1.09
     they
    0.98
    はこの
    0.96
     this
    0.96
     like
    0.95
    ;
    0.93
     had
    0.91
     उन
    0.90
     could
    0.88
    Activations Density 0.001%

    No Known Activations