© 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. 19523
    Prev
    Next
    INDEX
    Explanations

    imponer baumwolle

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

    The neuron is detecting apostrophes in contractions and possessive forms.

    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
     this
    -2.48
     make
    -2.13
     one
    -2.05
     both
    -2.03
     before
    -1.98
     several
    -1.96
     every
    -1.92
     putting
    -1.91
     after
    -1.91
     there
    -1.89
    POSITIVE LOGITS
     baumwolle
    2.20
     $-$
    2.05
    '
    2.02
     unſ
    1.84
    ю
    1.83
    ఌ
    1.82
    '">
    1.82
     imponer
    1.80
    ）
    1.78
     '-
    1.77
    Activations Density 0.112%

    No Known Activations