© 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. 22-GEMMASCOPE-RES-131K
    7. 15205
    Prev
    Next
    INDEX
    Explanations

    collaboration and joint initiatives

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

    The neuron flags formal institutional or organizational mentions—especially agency names, program acronyms, and partnership/commissioning announcements.

    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
     our
    -1.55
     by
    -1.55
     himself
    -1.12
     time
    -1.05
     while
    -0.99
    帜
    -0.97
     his
    -0.96
    夙
    -0.94
     any
    -0.94
     we
    -0.92
    POSITIVE LOGITS
     together
    1.77
     jointly
    1.71
    joint
    1.50
    共同
    1.49
    together
    1.45
     gemeinsam
    1.41
     совмест
    1.37
    Together
    1.36
     مشتر
    1.29
     совме
    1.27
    Activations Density 0.081%

    No Known Activations