© 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. 66382
    Prev
    Next
    INDEX
    Explanations

    libraries and librarians

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

    The neuron specifically fires on mentions of libraries or library‐related services.

    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
     of
    -1.20
     processions
    -1.13
    cademy
    -1.09
    )
    -1.08
    </h4>
    -1.08
    ございません
    -1.06
    ,
    -1.06
    thodoxy
    -1.05
     continuación
    -1.04
    </em>
    -1.03
    POSITIVE LOGITS
     library
    1.45
     librarians
    1.38
     libraries
    1.37
    บริการ
    1.27
    hamed
    1.23
     librarian
    1.23
    資源
    1.23
    検索
    1.16
    ampunk
    1.16
    expiresIn
    1.13
    Activations Density 0.035%

    No Known Activations