© 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. 22-GEMMASCOPE-RES-131K
    7. 93300
    Prev
    Next
    INDEX
    Explanations

    groups and assignments

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

    The neuron fires on mentions of people organized into groups—especially counting or describing student/participant group sessions.

    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
     TUESDAY
    -1.11
     bakar
    -1.11
    ::__
    -1.05
     WEDNESDAY
    -1.04
     das
    -1.03
     kull
    -1.02
    7
    -1.02
     https
    -1.02
     katt
    -1.02
     kolon
    -1.00
    POSITIVE LOGITS
     each
    1.39
    paravant
    1.23
     their
    1.23
     Dicht
    1.22
    phate
    1.20
     jejich
    1.20
     everyone
    1.20
    Ако
    1.18
     obyvateľov
    1.14
     vienas
    1.13
    Activations Density 0.009%

    No Known Activations