© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60603
    Prev
    Next
    INDEX
    Explanations

    us and we

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

    The neuron fires on first-person plural pronouns (e.g. “us,” “we,” etc.).

    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
     only
    -1.69
     himself
    -1.66
     for
    -1.62
     before
    -1.59
     two
    -1.55
     itself
    -1.52
     one
    -1.51
     with
    -1.50
     has
    -1.49
     is
    -1.46
    POSITIVE LOGITS
     ourselves
    3.08
     داریم
    1.88
    roughly
    1.72
    itize
    1.66
    olved
    1.66
    酐
    1.56
    hores
    1.55
    zembro
    1.55
    鲼
    1.55
    skou
    1.53
    Activations Density 2.012%

    No Known Activations