© 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. 22-GEMMASCOPE-RES-131K
    7. 9509
    Prev
    Next
    INDEX
    Explanations

    link to

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

    The neuron detects occurrences of hyperlink-related instructions or the word “link,” i.e. text directing the reader to click or follow a link.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    They
    -1.20
     bună
    -1.16
     oamenii
    -1.11
     oxígeno
    -1.08
     combustível
    -1.06
     toată
    -1.05
     învă
    -1.05
    早在
    -1.05
     viață
    -1.03
     ziua
    -1.00
    POSITIVE LOGITS
     for
    1.18
     ссылке
    1.17
     http
    1.09
    www
    1.08
    ländern
    1.06
     if
    1.02
     https
    1.01
    ≧
    1.00
     or
    0.98
     www
    0.97
    Activations Density 0.021%

    No Known Activations