© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67005
    Prev
    Next
    INDEX
    Explanations

    topics in games and software

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

    The neuron is strongly activated by proper nouns and named entities (e.g. game titles, character or place 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
     zowel
    -1.54
     公园
    -1.29
     Palembang
    -1.27
    能夠
    -1.26
    🤣🤣🤣
    -1.25
    ୂ
    -1.23
     Envi
    -1.23
    ುವ
    -1.23
    盪
    -1.23
     loch
    -1.22
    POSITIVE LOGITS
     even
    1.45
     даже
    1.29
    ;
    1.21
     nawet
    1.20
     ש
    1.18
    甚至
    1.17
     –
    1.14
    atoday
    1.13
    ↵↵↵
    1.10
     =
    1.10
    Activations Density 0.031%

    No Known Activations