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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21706
    Prev
    Next
    INDEX
    Explanations

    calling super or base

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

    The neuron is triggered by occurrences of the “super” keyword (i.e. calls or references to a superclass method).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     for
    -2.39
     even
    -1.86
    
    -1.81
     Pokud
    -1.77
     any
    -1.73
     on
    -1.71
     reconocido
    -1.70
     between
    -1.70
     This
    -1.68
    柺
    -1.63
    POSITIVE LOGITS
    8
    2.38
    ’
    2.28
    3
    2.27
    7
    2.23
    9
    2.11
    2
    2.09
    6
    2.02
    5
    1.90
     mentre
    1.89
     zoude
    1.86
    Activations Density 0.006%

    No Known Activations