© 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. 26190
    Prev
    Next
    INDEX
    Explanations

    given names and surnames

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

    This neuron detects occurrences of “name” and related metadata in dictionary‐ or encyclopedia‐style entries about personal names.

    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
    谙
    -1.20
     operation
    -1.20
     system
    -1.20
     capability
    -1.13
     required
    -1.13
    вил
    -1.13
    完成です
    -1.08
     estacionamiento
    -1.07
     auteurs
    -1.07
     during
    -1.07
    POSITIVE LOGITS
     ویتامین
    1.68
     religieuses
    1.47
     masculinos
    1.23
    宝物
    1.23
     сахара
    1.23
     витами
    1.20
     communs
    1.19
    醯
    1.19
     ſon
    1.18
     cukru
    1.18
    Activations Density 0.018%

    No Known Activations