© 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. 10-GEMMASCOPE-RES-131K
    7. 73815
    Prev
    Next
    INDEX
    Explanations

    common nouns

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

    This neuron detects two-word noun phrases consisting of a determiner or possessive pronoun immediately followed by a noun.

    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
     must
    -1.35
     how
    -1.31
    in
    -1.31
     применение
    -1.31
    要不然
    -1.27
     potrzeby
    -1.27
     какие
    -1.26
    いかがでしたか
    -1.23
     duże
    -1.21
     manguera
    -1.21
    POSITIVE LOGITS
     other
    2.00
     págs
    1.60
     menant
    1.54
    牁
    1.51
     fua
    1.51
     lainnya
    1.51
     Chambres
    1.51
     gita
    1.50
     |
    1.48
    zelve
    1.46
    Activations Density 0.009%

    No Known Activations