© 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. 22-GEMMASCOPE-RES-131K
    7. 15709
    Prev
    Next
    INDEX
    Explanations

    authors and collaborators

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

    The neuron strongly activates on numeric and citation‐style tokens (years, volume/page numbers, article identifiers) in references.

    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
    Sculpture
    -1.06
    st
    -1.05
     transférez
    -1.02
    Documentary
    -1.00
     kimdir
    -0.99
    いたしました
    -0.98
    اااا
    -0.94
    сение
    -0.94
     églises
    -0.94
     abiye
    -0.93
    POSITIVE LOGITS
     ambayo
    1.19
     KeyCode
    1.06
    ―
    1.05
    1.03
    çoit
    1.03
    𝓲
    1.00
    ब
    1.00
     IEnumerator
    0.99
    āci
    0.99
    —
    0.98
    Activations Density 0.004%
    No Known Activations