© 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. 32763
    Prev
    Next
    INDEX
    Explanations

    compound noun phrases

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

    The neuron activates on specialized technical or scientific terms.

    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
    橈
    -1.27
    Transcripción
    -1.25
    ệu
    -1.20
    𓇼
    -1.19
    żył
    -1.17
    北欧
    -1.16
    夢見
    -1.16
    Sailor
    -1.14
    ꔛ
    -1.12
    ※※
    -1.09
    POSITIVE LOGITS
     alojamientos
    1.31
    设计的
    1.16
     muebles
    1.16
     calefacción
    1.09
    化した
    1.08
     plazos
    1.08
    ındaki
    1.04
    方面的
    1.03
    出来的
    1.03
    λους
    1.02
    Activations Density 0.325%

    No Known Activations