© 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. 1892
    Prev
    Next
    INDEX
    Explanations

    aren't

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

    The neuron detects occurrences of the negation contraction “aren’t.”

    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
     alebo
    -2.63
    焄
    -2.39
     is
    -2.39
    倌
    -2.28
     betale
    -2.27
     bidra
    -2.23
    
    -2.23
    a
    -2.19
    ]
    -2.13
    Ἢ
    -2.13
    POSITIVE LOGITS
     are
    2.61
     Перейти
    2.48
    </sub>
    2.42
    Sebagai
    2.41
     sebag
    2.41
     ungew
    2.28
    </i>
    2.25
    ка
    2.22
    that
    2.22
    :
    2.20
    Activations Density 0.008%

    No Known Activations