© 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. 22-GEMMASCOPE-RES-131K
    7. 33322
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    The neuron strongly activates on sequences of personal pronouns (I, he, they, etc.) together with verbs—especially past-tense or speech-reporting verbs—i.e. bits of narrative or reported-speech.

    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
    okolade
    -0.94
    assertFalse
    -0.92
    lden
    -0.91
     chưa
    -0.90
    зов
    -0.87
    tellung
    -0.86
     ゴールド
    -0.85
    oplasma
    -0.85
    iosos
    -0.84
    əl
    -0.84
    POSITIVE LOGITS
     всеки
    1.02
     frequent
    0.96
    いれば
    0.90
    ✏
    0.88
    searchable
    0.86
     akti
    0.83
    ⣰
    0.80
     familiarity
    0.79
     funcionários
    0.79
     풍
    0.79
    Activations Density 0.055%

    No Known Activations