© 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. 14752
    Prev
    Next
    INDEX
    Explanations

    everyone knows

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

    This neuron detects inclusive, generalizing phrases that express a shared or universal experience—especially constructions like “we all …” or “everyone ….”

    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
     everything
    -1.34
     only
    -1.23
     other
    -1.21
     itself
    -1.10
     nothing
    -1.04
     your
    -1.02
     buka
    -1.01
     instead
    -1.01
     RSSSF
    -0.97
     atriz
    -0.94
    POSITIVE LOGITS
     első
    1.05
     mengakui
    1.02
    kann
    1.00
     <",
    0.99
    dsky
    0.98
    +#
    0.98
    öner
    0.97
     />";
    0.96
    Someone
    0.94
     عندما
    0.94
    Activations Density 0.033%

    No Known Activations