© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70457
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron fires on explicit data-collection or stream types (like RDD, DStream, QuerySet, Observable, IEnumerable, etc.) 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_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
    k
    -1.75
    7
    -1.66
    h
    -1.59
    b
    -1.58
    the
    -1.56
    g
    -1.54
    f
    -1.48
    so
    -1.47
     ersten
    -1.45
    6
    -1.44
    POSITIVE LOGITS
     of
    1.88
     MÁS
    1.43
     обслуживание
    1.39
    ezy
    1.38
     kaikki
    1.32
     LAYER
    1.30
     dwóch
    1.30
    읖
    1.29
     edifício
    1.28
     only
    1.27
    Activations Density 0.018%

    No Known Activations