© 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. 85640
    Prev
    Next
    INDEX
    Explanations

    names of people and bands

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

    The neuron activates on proper names—especially personal or band/artist 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
    。
    -1.27
    ǐ
    -1.23
     erscheinen
    -1.18
     törvény
    -1.18
     szybko
    -1.14
    //@
    -1.12
     faves
    -1.11
    Litteratur
    -1.09
     Johannesburg
    -1.09
    نجليزية
    -1.09
    POSITIVE LOGITS
    旆
    1.28
     gegebenen
    1.20
    丁寧に
    1.19
    <td>
    1.18
     umgangssprach
    1.17
     gegenwär
    1.15
    等着
    1.13
    1.12
     ノー
    1.10
     participer
    1.09
    Activations Density 0.127%

    No Known Activations