© 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. 34-GEMMASCOPE-RES-131K
    7. 84807
    Prev
    Next
    INDEX
    Explanations

    names ending in es or similar

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

    This neuron fires on tokens containing the letter sequence “es,” particularly at the ends of names and 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_34/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
     highly
    -0.79
    apropri
    -0.75
    tü
    -0.71
    Welp
    -0.69
    these
    -0.69
    def
    -0.68
    迎来
    -0.68
     expertly
    -0.68
     absurdo
    -0.67
     suitable
    -0.65
    POSITIVE LOGITS
    ssss
    1.00
    ssssssss
    0.98
    nas
    0.95
    ss
    0.91
    ned
    0.91
    nes
    0.90
    sians
    0.88
    ionado
    0.88
    ters
    0.88
    nice
    0.88
    Activations Density 0.189%

    No Known Activations