© 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. 10-GEMMASCOPE-RES-131K
    7. 9713
    Prev
    Next
    INDEX
    Explanations

    German plurals and language

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

    The neuron responds to tokens ending in an “s” suffix (e.g. English plurals or German inflectional endings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -3.58
    2
    -3.17
    the
    -2.73
    ing
    -2.69
    k
    -2.69
     ''
    -2.63
    s
    -2.56
    ophageal
    -2.56
    i
    -2.50
    --
    -2.45
    POSITIVE LOGITS
     solteiro
    2.63
    玙
    2.55
    ᐕ
    2.42
    퐿
    2.34
    訁
    2.34
     Handeln
    2.31
     tiệc
    2.31
    ☫
    2.28
    служба
    2.27
    ᠌
    2.23
    Activations Density 0.002%

    No Known Activations