© 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. 71165
    Prev
    Next
    INDEX
    Explanations

    giving praise

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

    The neuron primarily detects the word “praise” (and its inflected forms) in the text.

    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
    </strong>
    -2.19
     findet
    -2.11
    郿
    -2.08
    ?”
    -2.06
     you
    -2.02
     savvy
    -2.00
    ?’
    -1.97
    </h3>
    -1.96
    },
    -1.95
    鹛
    -1.93
    POSITIVE LOGITS
    This
    2.02
    葙
    2.00
    o
    1.96
    
    1.93
     хорошее
    1.88
     STARTING
    1.84
    وأضاف
    1.84
     zimowe
    1.80
     一覧
    1.77
    According
    1.77
    Activations Density 0.006%

    No Known Activations