© 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. 22-GEMMASCOPE-RES-131K
    7. 71951
    Prev
    Next
    INDEX
    Explanations

    trust and trustworthiness

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

    The neuron fires strongly on common high‐frequency function words—especially short conjunctions, articles, and prepositions (e.g. “and,” “the,” “of,” “in”).

    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
    urora
    -1.13
     comprensión
    -1.11
    actéristi
    -1.06
     tekanan
    -1.04
     onResponse
    -1.04
    parseColor
    -1.03
     considérons
    -1.01
     geluid
    -1.00
     definición
    -1.00
    acją
    -1.00
    POSITIVE LOGITS
     trust
    2.58
    trust
    2.06
     trusting
    2.05
     TRUST
    1.80
     Trust
    1.80
     trusted
    1.77
    Trust
    1.73
     confiance
    1.73
     trustworthy
    1.69
     distrust
    1.66
    Activations Density 0.025%

    No Known Activations