© 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. 68424
    Prev
    Next
    INDEX
    Explanations

    one of the [abstract nouns]

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

    The main thing this neuron does is find common nouns in their plural form.

    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
     inaugur
    -1.35
    すみません
    -1.34
     Dinas
    -1.27
     appris
    -1.25
     solchen
    -1.24
    жар
    -1.24
     devast
    -1.23
     contempl
    -1.21
     ſont
    -1.21
    だけでなく
    -1.20
    POSITIVE LOGITS
     that
    2.14
     in
    1.81
     you
    1.73
     we
    1.61
     of
    1.55
     if
    1.43
     get
    1.43
     new
    1.36
     because
    1.35
     which
    1.34
    Activations Density 0.060%

    No Known Activations