© 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. 98360
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron is keyed to negative contractions, in particular spotting the “n’t” (as in “don’t”) suffix.

    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
     Пото
    -0.93
    ϶
    -0.91
    居家
    -0.91
    的基本
    -0.89
    ┏
    -0.88
     Young
    -0.88
     lush
    -0.87
    ISHOP
    -0.85
     attractive
    -0.85
     weathered
    -0.84
    POSITIVE LOGITS
     entrenar
    1.05
    がとても
    1.01
     всички
    1.01
     ہوا
    1.00
     statunit
    0.98
    我覺得
    0.97
     travaillons
    0.96
     intervenciones
    0.94
     всичко
    0.94
    vieran
    0.93
    Activations Density 0.007%

    No Known Activations