© 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. 36135
    Prev
    Next
    INDEX
    Explanations

    interrelated, linked, connected

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

    The neuron detects terms that express interconnection or linkage (e.g. interrelated, interlock, connected, linked, coupled).

    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
     DialogInterface
    -1.15
    ༈
    -1.14
    zionamento
    -1.13
     MotionEvent
    -1.09
     forskellige
    -1.06
     ț
    -1.03
     değişik
    -1.03
     noget
    -1.03
     Canadá
    -1.02
     novos
    -1.02
    POSITIVE LOGITS
     interrelated
    1.23
     inseparable
    1.16
     interdependent
    1.06
     chaque
    1.01
     rénovation
    0.98
    セット
    0.98
     inextrica
    0.94
    tldr
    0.94
    şap
    0.94
     взаимо
    0.94
    Activations Density 0.031%

    No Known Activations