© 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. 16724
    Prev
    Next
    INDEX
    Explanations

    prerequisite, another, reason, key

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

    The neuron fires on noun phrases introduced by an indefinite article (“a” or “an”) that define or describe the subject.

    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
    相關
    -0.89
     and
    -0.88
     Cupertino
    -0.88
    เป็น
    -0.86
    hibition
    -0.85
    並不
    -0.85
    Cf
    -0.84
     عليك
    -0.84
    lider
    -0.84
    Количество
    -0.83
    POSITIVE LOGITS
     carinho
    1.23
     abraço
    1.19
     veritable
    1.15
     todėl
    1.10
     virš
    1.07
     nosso
    1.06
     espírito
    1.05
    katapos
    1.05
    &
    1.04
     jį
    1.03
    Activations Density 0.016%

    No Known Activations