© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100192
    Prev
    Next
    INDEX
    Explanations

    company or team names

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

    The neuron activates on capitalized names of organizations, companies, or other proper-entity tokens.

    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
    чня
    -1.16
     again
    -1.12
    пку
    -1.00
    tamia
    -0.99
    chaik
    -0.98
     meras
    -0.97
     schien
    -0.97
     hanya
    -0.96
     menim
    -0.96
     NYC
    -0.96
    POSITIVE LOGITS
     from
    1.16
     try
    1.16
     anklicken
    1.13
     determinados
    1.09
     each
    1.09
     rotación
    1.04
     through
    1.02
    つき
    1.02
     these
    1.02
    Semoga
    1.02
    Activations Density 0.292%

    No Known Activations