© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34727
    Prev
    Next
    INDEX
    Explanations

    pronoun + linking verb

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

    The neuron fires on occurrences of subject personal pronouns (he, it, they) when they’re immediately paired with a form of the verb “to be” (is, ’s, are, been).

    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
     significantly
    -1.00
     doesn
    -1.00
     없습니다
    -1.00
    却没有
    -0.90
     neither
    -0.88
    issens
    -0.88
     couldn
    -0.85
    provide
    -0.84
     didn
    -0.84
     shouldn
    -0.83
    POSITIVE LOGITS
     becomes
    1.00
     became
    0.97
     sido
    0.93
     gets
    0.90
     شده
    0.88
     terasa
    0.88
    czenie
    0.86
    πουργ
    0.85
     blevet
    0.84
     remained
    0.82
    Activations Density 0.029%

    No Known Activations