© 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. 34805
    Prev
    Next
    INDEX
    Explanations

    our offerings and services

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

    The neuron fires strongly on the first‐person plural possessive “our.”

    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
     some
    -1.08
     médaille
    -1.06
    orithmic
    -1.03
     its
    -1.00
     farbe
    -1.00
     our
    -1.00
    个人
    -0.96
    tım
    -0.96
    ный
    -0.95
     esigen
    -0.94
    POSITIVE LOGITS
     website
    1.45
     products
    1.42
     services
    1.34
     menu
    1.14
     product
    1.13
     service
    1.13
    m
    1.04
     output
    1.02
     customers
    1.01
     них
    1.00
    Activations Density 0.051%

    No Known Activations