© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34479
    Prev
    Next
    INDEX
    Explanations

    connecting actions and outcomes

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

    This neuron responds to words that denote cooperation, support, or communication (e.g. “and,” “communication,” “relate,” “help,” “lift,” “strengthen”).

    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
     from
    -1.10
     since
    -1.03
    masta
    -0.98
     cannot
    -0.97
    Adapun
    -0.90
     it
    -0.89
    ஃ
    -0.85
    RAINT
    -0.84
     ducato
    -0.84
    zionata
    -0.84
    POSITIVE LOGITS
     retirer
    1.12
     travailler
    1.03
     studia
    1.02
     siano
    1.00
     velha
    0.99
     sélectionner
    0.99
    serve
    0.96
     опять
    0.96
     backgroundColor
    0.95
     délib
    0.94
    Activations Density 0.030%

    No Known Activations