© 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. 42660
    Prev
    Next
    INDEX
    Explanations

    nay, neighbourhood, Hajduk

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

    The neuron is detecting occurrences of the character sequence “nay” (in standalone form or as part of larger words).

    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
    ?’
    -3.20
    ’,
    -2.80
     ‘‘
    -2.58
    煦
    -2.52
     sends
    -2.45
    적으로
    -2.42
     (‘
    -2.41
    ではまた
    -2.38
    ,’’
    -2.38
    }
    -2.38
    POSITIVE LOGITS
     glimmer
    2.33
     You
    2.31
     we
    2.31
    9
    2.27
     
    2.25
    想
    2.23
    ↵
    2.20
    )
    2.11
    妻子
    2.08
     suéter
    2.05
    Activations Density 0.002%

    No Known Activations