© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64316
    Prev
    Next
    INDEX
    Explanations

    United States patents and applications

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

    The neuron strongly activates on numeric identifiers and citation numbers (digits in legal/patent/document references).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     to
    -1.15
    -1.15
    amkeit
    -1.13
    -1.09
    anzen
    -1.09
    วันที่
    -1.05
    Ї
    -1.05
    中学校
    -1.04
     capot
    -1.03
    ﻷ
    -1.02
    POSITIVE LOGITS
    replyreport
    1.20
    шений
    1.19
     narkoba
    1.13
     muere
    1.10
    んですね
    1.09
     χρησιμοποι
    1.09
     Francji
    1.09
     forked
    1.09
    How
    1.08
    えっ
    1.07
    Activations Density 0.001%

    No Known Activations