© 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. 9520
    Prev
    Next
    INDEX
    Explanations

    external links

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

    The neuron consistently fires on the “External links” section heading at the end of articles—that is, it spots that specific footer heading.

    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
    {
    -2.59
     has
    -2.09
     crée
    -1.95
        
    -1.91
     and
    -1.85
    sisters
    -1.84
    ↵
    -1.78
     pensado
    -1.75
    '
    -1.74
    ],
    -1.70
    POSITIVE LOGITS
    8
    2.52
    3
    2.23
    6
    2.22
    ܇
    2.14
    我还是
    2.08
    7
    2.06
     erklär
    2.05
    
    2.02
    9
    2.02
    OUTUBE
    2.02
    Activations Density 0.003%

    No Known Activations