© 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. 36710
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by to verb

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

    This neuron activates on words that refer to people (especially pronouns like me, you, us, them, users, students, his).

    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
     canlynol
    -1.02
    Jogo
    -0.97
    fasis
    -0.91
     présidenti
    -0.90
    Etape
    -0.90
    Ār
    -0.88
     Messina
    -0.85
    monių
    -0.84
     appris
    -0.84
    HasColumnName
    -0.83
    POSITIVE LOGITS
    ca
    0.97
    il
    0.90
     obligated
    0.86
    me
    0.85
     Theorems
    0.84
    din
    0.83
    ting
    0.82
     to
    0.81
    cs
    0.81
    ’’
    0.80
    Activations Density 0.086%

    No Known Activations