© 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. 34-GEMMASCOPE-RES-131K
    7. 93196
    Prev
    Next
    INDEX
    Explanations

    internet and digital media

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

    The neuron is keyed to longer, content‐bearing words (i.e. mid- to high-frequency tokens of six or more letters) rather than short function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     audiobook
    -1.14
     audiobooks
    -1.09
    电视剧
    -0.93
    EmployeeId
    -0.91
    ：（
    -0.91
    Audiobook
    -0.90
     растение
    -0.89
    近期
    -0.89
     changelog
    -0.88
    録画
    -0.88
    POSITIVE LOGITS
     Internet
    3.72
     internet
    3.61
     online
    3.50
    Internet
    3.00
    internet
    2.89
     cyber
    2.77
     Online
    2.58
     digital
    2.55
    online
    2.47
     web
    2.38
    Activations Density 0.098%

    No Known Activations