© 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. 75329
    Prev
    Next
    INDEX
    Explanations

    properties and identifiers

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

    The neuron fires on occurrences of C#-style property accessors (especially the “get” keyword in property definitions).

    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
    -1.88
     if
    -1.63
     of
    -1.59
    if
    -1.48
     our
    -1.41
     then
    -1.35
    :
    -1.30
    !
    -1.30
     all
    -1.30
    ,
    -1.27
    POSITIVE LOGITS
    alers
    1.66
    ⟐
    1.65
     reacciones
    1.64
    考え方
    1.52
     jiné
    1.50
     mejoras
    1.49
     lidé
    1.48
    Dış
    1.47
    Ayrıca
    1.45
     innych
    1.41
    Activations Density 0.074%

    No Known Activations