© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7536
    Prev
    Next
    INDEX
    Explanations

    academic and religious professions

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

    The neuron flags terms associated with formal medieval scholastic and theological discourse (e.g. disputation, monastic, Franciscan, tenets of faith).

    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
     you
    -1.48
     frappé
    -1.31
     annoncé
    -1.27
     refusé
    -1.26
    vább
    -1.25
     welches
    -1.21
     petits
    -1.18
     choisi
    -1.16
     quien
    -1.15
     \
    -1.14
    POSITIVE LOGITS
     must
    1.16
    TAINMENT
    1.12
     devono
    1.09
    適量
    1.09
     things
    1.09
     higher
    1.08
     contex
    1.07
     abel
    1.06
     catto
    1.06
     adanya
    1.05
    Activations Density 0.054%

    No Known Activations