© 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. 522
    Prev
    Next
    INDEX
    Explanations

    code comments and definitions

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

    The neuron is essentially inactive on these inputs and does not detect or respond to any token patterns.

    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
     parfüm
    -2.23
    ⵌ
    -2.08
     kering
    -1.99
     hisz
    -1.99
     organik
    -1.99
     anún
    -1.98
     phénom
    -1.98
     relâche
    -1.96
     skolen
    -1.96
     rése
    -1.95
    POSITIVE LOGITS
     to
    2.75
     This
    2.30
     If
    2.28
    !
    2.00
     now
    1.96
     A
    1.86
    d
    1.86
    if
    1.84
     for
    1.82
     not
    1.80
    Activations Density 0.042%

    No Known Activations