© 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. 128918
    Prev
    Next
    INDEX
    Explanations

    click to visit or access

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

    The neuron detects link– or call-to-action trigger words that prompt the reader to click, visit, download, access, or otherwise engage with a hyperlink.

    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
     damned
    -1.21
     infinita
    -1.19
    の情報
    -1.19
    erequisite
    -1.17
    劣化
    -1.16
     gordo
    -1.14
    Informazioni
    -1.13
     return
    -1.13
     discretion
    -1.12
     Vielzahl
    -1.12
    POSITIVE LOGITS
    mereka
    1.31
     είναι
    1.27
    Mereka
    1.23
     about
    1.20
     dlaczego
    1.13
    ┤
    1.13
     Kommission
    1.13
    ～♪
    1.13
    椀
    1.11
    ～！
    1.10
    Activations Density 0.022%

    No Known Activations