© 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. 34324
    Prev
    Next
    INDEX
    Explanations

    legal or official titles

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

    The neuron detects mentions of institutional ethics or regulatory approvals (e.g., institutional review board approval and study protocol authorization).

    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
    外科
    -0.86
     RESP
    -0.84
     Réunion
    -0.83
     Epistle
    -0.82
     dames
    -0.82
    eronau
    -0.82
     LUMI
    -0.82
     sobri
    -0.82
    amblea
    -0.81
    ffichage
    -0.80
    POSITIVE LOGITS
     and
    1.48
     owner
    0.97
     ljudi
    0.93
     stessa
    0.90
     people
    0.87
    人員
    0.84
     najbol
    0.83
     práci
    0.83
     ayudas
    0.82
    fej
    0.82
    Activations Density 0.099%

    No Known Activations