© 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. 71902
    Prev
    Next
    INDEX
    Explanations

    java collections and vectors

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

    The neuron fires whenever the Java class name “ArrayList” appears (e.g. in import statements or type/constructor uses).

    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
     on
    -1.63
     in
    -1.27
     Rá
    -1.25
     Without
    -1.20
     Desenvolvimento
    -1.15
     at
    -1.15
     Ş
    -1.13
     without
    -1.12
    ırken
    -1.09
     Lainnya
    -1.09
    POSITIVE LOGITS
     Hp
    1.12
     finanzi
    1.06
     Aps
    1.05
     ざ
    1.03
     lorsque
    1.02
    鈥
    1.02
     praticamente
    1.02
     coûts
    1.01
     verzame
    1.00
     gemeinsam
    0.98
    Activations Density 0.003%

    No Known Activations