© 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. 61167
    Prev
    Next
    INDEX
    Explanations

    Nikon, Patti, +/-

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

    This neuron responds to capitalized proper names and technical identifiers (e.g., personal names, brand/model names, class names).

    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
    ༀ
    -2.80
    榦
    -2.50
    咈
    -2.47
    殽
    -2.39
    秝
    -2.36
    ный
    -2.34
    ቍ
    -2.31
     setEmail
    -2.28
     maken
    -2.27
    ⤥
    -2.27
    POSITIVE LOGITS
    是個
    2.95
    柞
    2.63
    不宜
    2.52
    是我的
    2.45
     contextos
    2.41
    是想
    2.41
     trough
    2.38
    纐
    2.38
     może
    2.38
     wachsen
    2.36
    Activations Density 0.006%

    No Known Activations