© 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. 14891
    Prev
    Next
    INDEX
    Explanations

    theological seminaries and American history

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

    The neuron detects mentions of theological seminaries or related religious-education institutions.

    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
     The
    -3.06
    饪
    -2.83
     unſ
    -2.77
    '
    -2.77
     But
    -2.63
    佉
    -2.45
     uſed
    -2.33
    colgante
    -2.33
    zaSy
    -2.31
     startling
    -2.28
    POSITIVE LOGITS
    ).
    2.45
    ྂ
    2.34
    ſſer
    2.25
    縯
    2.20
    ﾋ
    2.17
     ランド
    2.16
    鏨
    2.14
     土産
    2.09
    圄
    2.09
    彗
    2.08
    Activations Density 0.003%

    No Known Activations