© 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. 130237
    Prev
    Next
    INDEX
    Explanations

    instance keyword

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the token “Instance.”

    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
     conç
    -2.42
    馕
    -2.33
    ﻞ
    -2.33
    and
    -2.31
    㩒
    -2.22
    How
    -2.20
     personnalisées
    -2.19
    ⋰
    -2.13
     oreja
    -2.13
    where
    -2.13
    POSITIVE LOGITS
     was
    3.02
    
    2.70
    wiście
    2.67
     is
    2.48
    さんの
    2.41
    潆
    2.41
     им
    2.39
    ])){
    2.27
    谟
    2.27
    䊏
    2.23
    Activations Density 0.003%

    No Known Activations