© 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. 71051
    Prev
    Next
    INDEX
    Explanations

    way to do something

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

    The neuron fires strongly on non-stopword content tokens—i.e. domain-relevant nouns and verbs (especially longer, technical words) rather than on common function words.

    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
     беже
    -1.13
     yalnız
    -0.96
     migh
    -0.94
    elded
    -0.93
     trabajó
    -0.92
    Gilla
    -0.91
     veroor
    -0.90
     asesinado
    -0.90
     recibió
    -0.90
     patří
    -0.89
    POSITIVE LOGITS
     approach
    1.36
     things
    1.21
     подход
    0.98
     which
    0.94
     such
    0.93
     albic
    0.93
     neder
    0.91
     vader
    0.91
     it
    0.89
     this
    0.88
    Activations Density 0.106%

    No Known Activations