© 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. 10-GEMMASCOPE-RES-131K
    7. 69546
    Prev
    Next
    INDEX
    Explanations

    ending or cessation

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

    This neuron fires on words and phrases indicating cessation or stopping, especially forms of “cease/cessat-.”

    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
    ⧠
    -2.95
    仨
    -2.53
     réserver
    -2.52
    他会
    -2.44
    俛
    -2.39
    垍
    -2.33
    
    -2.30
    明るく
    -2.28
     indican
    -2.28
    明るい
    -2.28
    POSITIVE LOGITS
    你
    2.86
    ↵
    2.81
    </em>
    2.73
    如果
    2.45
    ’
    2.42
     With
    2.41
    是
    2.28
    2
    2.28
    );
    2.27
     How
    2.25
    Activations Density 0.007%

    No Known Activations