© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90723
    Prev
    Next
    INDEX
    Explanations

    as a part

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

    This neuron detects “as a/an … ” constructions—i.e. it activates on the words in noun phrases introduced by “as a” or “as an.”

    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
    😵
    -1.05
     emble
    -1.02
    用来
    -1.02
    😓
    -1.02
    bindung
    -1.01
    😖
    -0.99
    issé
    -0.97
    相關
    -0.96
     cial
    -0.96
    😪
    -0.94
    POSITIVE LOGITS
     a
    2.38
     separate
    1.65
     an
    1.52
     part
    1.46
     either
    1.43
     if
    1.32
     seperate
    1.24
     отдель
    1.22
     tatuagem
    1.16
     terpisah
    1.16
    Activations Density 0.112%

    No Known Activations