© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130379
    Prev
    Next
    INDEX
    Explanations

    groups interacting with services

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

    The neuron fires on high-level institutional and systemic terms—especially those related to public health, policy, regulation, and societal or healthcare systems.

    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
     without
    -1.34
     about
    -1.21
    旖
    -1.13
     over
    -1.11
     as
    -1.11
     comunión
    -1.10
    缜
    -1.08
     there
    -1.07
     българ
    -1.05
    uspiel
    -1.05
    POSITIVE LOGITS
     levantó
    1.06
     esquer
    1.06
     miró
    1.05
    Daha
    1.05
     récupérer
    1.03
    看上去
    1.02
    miyorum
    1.02
     даже
    1.00
     entries
    0.98
    utuhan
    0.98
    Activations Density 0.582%

    No Known Activations