© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83933
    Prev
    Next
    INDEX
    Explanations

    addictive things, substances, or tunes

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

    The main thing this neuron does is detect mentions of addiction—especially the word “addictive” and its variants.

    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
     then
    -2.33
    ’
    -2.30
     the
    -2.17
    s
    -2.09
    <bos>
    -2.03
    繽
    -1.97
        
    -1.96
    
    -1.96
     ventured
    -1.95
    U
    -1.90
    POSITIVE LOGITS
     addictive
    2.23
    你
    2.06
    他的
    2.02
    sieger
    1.91
    жении
    1.88
     yine
    1.87
    自己的
    1.85
     Jadi
    1.80
     Estas
    1.80
     relieve
    1.80
    Activations Density 0.003%

    No Known Activations