© 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. 130389
    Prev
    Next
    INDEX
    Explanations

    names and following words

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

    The neuron responds strongly to capitalized tokens, especially proper names and other named-entity 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
     they
    -2.97
    嬋
    -2.89
    栳
    -2.88
    倶楽部
    -2.78
    躥
    -2.70
    鶿
    -2.63
    要不然
    -2.59
    鲧
    -2.50
    Ꞓ
    -2.45
    柃
    -2.45
    POSITIVE LOGITS
    y
    3.30
     In
    2.78
    危害
    2.73
    
    2.70
    提出
    2.63
     cortesía
    2.59
     После
    2.58
     dasarnya
    2.56
    担任
    2.53
     That
    2.45
    Activations Density 0.011%

    No Known Activations