© 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. 34-GEMMASCOPE-RES-131K
    7. 87166
    Prev
    Next
    INDEX
    Explanations

    organization or entity existed

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

    This neuron responds strongly to relative‐clause introducers and sentence‐linking pronouns (e.g. “that,” “which,” “it”) used to continue or define entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Personally
    -1.05
     mereka
    -1.02
    ҹ
    -0.96
     ktorí
    -0.94
    шных
    -0.91
     všetko
    -0.90
     karier
    -0.90
     persönlich
    -0.89
     ideen
    -0.89
     kteří
    -0.88
    POSITIVE LOGITS
     exist
    2.06
     exists
    1.95
     existed
    1.80
     existence
    1.60
     function
    1.60
     operate
    1.51
     consists
    1.45
     itself
    1.41
     functions
    1.34
     survive
    1.34
    Activations Density 0.155%

    No Known Activations