© 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. 10-GEMMASCOPE-RES-131K
    4. 80826
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    The neuron fires on subject-pronoun phrases (like “she was,” “we’ve been,” “he got,” “they reported,” “it has,” etc.), i.e. personal pronouns used with their auxiliary or main verbs.

    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
     they
    -1.30
     blau
    -1.23
     groote
    -1.20
    ↵
    -1.16
     then
    -1.15
     chúng
    -1.15
     holz
    -1.12
     ")");
    -1.12
    ichert
    -1.09
     abbiamo
    -1.09
    POSITIVE LOGITS
     encontró
    1.02
    Prosecutors
    1.02
    нью
    1.02
    ündigung
    1.01
     ľ
    1.00
     ジャケット
    1.00
     wyłącznie
    1.00
    aziland
    1.00
    യി
    1.00
    このような
    0.98
    Activations Density 0.097%

    No Known Activations