© 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. 22-GEMMASCOPE-RES-131K
    7. 39518
    Prev
    Next
    INDEX
    Explanations

    titles or beginning phrases

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

    The neuron detects C# code that uses Unity’s Editor APIs (e.g. UnityEditor namespaces, CustomPropertyDrawer attributes, and GUI/Editor methods).

    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
     pazi
    -1.24
     天空
    -1.21
     corect
    -1.14
     to
    -1.13
    pensione
    -1.13
     Geografía
    -1.13
    çadas
    -1.12
     vocale
    -1.09
     myndig
    -1.09
    ⓪
    -1.09
    POSITIVE LOGITS
     at
    1.39
    ू
    1.13
     lámina
    1.13
     siquiera
    1.11
     up
    1.09
    ietal
    1.08
    czej
    0.99
     flotante
    0.99
    Spline
    0.99
    曲は
    0.98
    Activations Density 0.004%

    No Known Activations