© 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. 39995
    Prev
    Next
    INDEX
    Explanations

    central

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

    The neuron detects occurrences of “central” (and its variants like “centrally,” “centrality,” etc.) in the text.

    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
     extremamente
    -1.80
    ÖN
    -1.49
    鶿
    -1.46
     cambiando
    -1.42
    坶
    -1.41
    ๖
    -1.40
    ſes
    -1.39
     Gibt
    -1.38
     validamos
    -1.38
    quelles
    -1.37
    POSITIVE LOGITS
    on
    1.95
    central
    1.72
    th
    1.65
     central
    1.64
    at
    1.57
    an
    1.56
    center
    1.54
    while
    1.53
     Central
    1.50
    when
    1.50
    Activations Density 0.056%

    No Known Activations