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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3193
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    This neuron detects two‐word spans where a personal pronoun (especially “you” or “he”) is immediately followed by a verb (often an auxiliary or action verb).

    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
     должны
    -0.99
    과
    -0.95
    บอก
    -0.94
     always
    -0.94
     должно
    -0.93
     immediately
    -0.91
     در
    -0.91
    OWN
    -0.90
     olması
    -0.90
    </strong>
    -0.85
    POSITIVE LOGITS
     indeed
    1.20
    急忙
    1.13
    indeed
    1.08
     houve
    1.07
     بابا
    1.02
    файл
    1.02
    Indeed
    0.99
    année
    0.96
    botas
    0.94
    lofen
    0.94
    Activations Density 0.054%

    No Known Activations