© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13108
    Prev
    Next
    INDEX
    Explanations

    information retrieval

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

    This neuron detects terminology and references related to information‐retrieval systems (e.g. “IR,” “information retrieval,” “search engine,” “ranked list,” “full‐text searching”).

    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
    chiere
    -1.52
     meist
    -1.52
    ждать
    -1.49
     Púb
    -1.48
    ⚋
    -1.39
    orteur
    -1.38
     bietet
    -1.30
     involvement
    -1.30
     inicia
    -1.28
    ógicos
    -1.27
    POSITIVE LOGITS
    =
    1.32
    i
    1.30
    e
    1.29
    \
    1.15
     somente
    1.15
     Nachmittag
    1.15
    ⊳
    1.13
     felhasznál
    1.09
     szár
    1.08
     deverá
    1.06
    Activations Density 0.031%

    No Known Activations