© 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. 22-GEMMASCOPE-RES-131K
    7. 104316
    Prev
    Next
    INDEX
    Explanations

    pronoun before verb

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

    This neuron detects third-person neuter pronouns (especially “it” and “they”) acting as formal subjects in expository sentences.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    しくは
    -1.20
     schuldig
    -1.12
    cepter
    -1.02
    Mű
    -1.00
     should
    -0.98
     Испании
    -0.96
    veria
    -0.96
    🖐
    -0.95
    ="&#
    -0.95
    endance
    -0.93
    POSITIVE LOGITS
     einerseits
    1.32
    Numerade
    1.14
    笵
    1.13
     represent
    1.08
    らしいです
    1.07
     représentants
    1.06
    lysninger
    1.06
     rappresenta
    1.04
    看他
    1.03
     pfle
    1.03
    Activations Density 0.040%

    No Known Activations