© 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. 34-GEMMASCOPE-RES-131K
    7. 117698
    Prev
    Next
    INDEX
    Explanations

    surnames following initials

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

    This neuron specializes in detecting middle‐initial abbreviations (a single capital letter plus a following period) in 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_34/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
     Viitattu
    -1.16
    TWO
    -1.14
    КИ
    -1.12
    ONE
    -1.11
    canActivate
    -1.09
     Europy
    -1.09
     SQLITE
    -1.06
    ДЕ
    -1.04
    Ｗ
    -1.03
     now
    -1.02
    POSITIVE LOGITS
     みた
    1.22
    补贴
    1.18
     in
    1.17
    Imgur
    1.11
    Provincia
    1.09
    鑷
    1.09
    Firing
    1.08
    增加了
    1.07
     changing
    1.05
     suele
    1.04
    Activations Density 0.091%

    No Known Activations