© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59411
    Prev
    Next
    INDEX
    Explanations

    name within

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

    This neuron fires on C# source code that uses the UnityEditor API (e.g. UnityEditor imports, attributes, and editor-specific classes/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_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
    NhanVien
    -1.45
     ciudadana
    -1.38
     św
    -1.38
     their
    -1.36
     victory
    -1.35
    SanPham
    -1.34
    Our
    -1.32
     海鮮
    -1.30
     employees
    -1.30
    民众
    -1.28
    POSITIVE LOGITS
     الجلد
    1.41
     you
    1.40
     掃除
    1.38
     theſe
    1.34
    Checkout
    1.26
     jendela
    1.23
    ilización
    1.22
    yecto
    1.20
    蝼
    1.16
    trusive
    1.15
    Activations Density 0.029%

    No Known Activations