© 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. 68593
    Prev
    Next
    INDEX
    Explanations

    "We" followed by verbs

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

    This neuron detects first-person plural self-references (e.g. “we,” “our,” “we’re,” “offer,” “encourage”) used in institutional or organizational statements.

    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
     probably
    -1.23
     could
    -1.16
     possibly
    -1.12
    更何况
    -1.01
     basically
    -1.00
     something
    -0.99
     perhaps
    -0.98
     maybe
    -0.98
    世帯
    -0.98
     whatever
    -0.98
    POSITIVE LOGITS
     you
    1.48
     вам
    1.23
     You
    1.16
    usata
    1.09
    了你
    1.09
     your
    1.08
     คุณ
    1.07
    alimentos
    1.05
    You
    1.05
    女主
    1.05
    Activations Density 0.043%

    No Known Activations