© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111773
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific naming conventions

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

    The neuron fires strongly on capitalized words (names and acronyms), effectively spotting proper nouns.

    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
    你有
    -2.64
    
    -2.52
    当我
    -2.41
     礼物
    -2.38
    .**
    -2.31
     oppose
    -2.31
    л
    -2.31
    当你
    -2.23
     defend
    -2.20
     embody
    -2.16
    POSITIVE LOGITS
    ing
    3.39
    遢
    3.13
    
    2.58
    咴
    2.52
    狞
    2.50
    栳
    2.44
    e
    2.42
     asegura
    2.34
    陆续
    2.31
    while
    2.30
    Activations Density 0.005%

    No Known Activations