© 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. 105701
    Prev
    Next
    INDEX
    Explanations

    proper names and brands

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

    The neuron is specialized to detect mentions of the Firestore database (i.e. the token “firestore”).

    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
     daarom
    -2.55
    亖
    -2.42
    囿
    -2.27
     voordat
    -2.25
     With
    -2.25
     For
    -2.23
    VIRGO
    -2.22
    nós
    -2.20
     namelijk
    -2.17
     intrepid
    -2.17
    POSITIVE LOGITS
    </b>
    2.73
    廰
    2.72
    ︕
    2.69
    㩒
    2.45
    笑话
    2.45
    鉭
    2.41
     шанс
    2.31
     diza
    2.31
    ский
    2.27
    こんばんは
    2.27
    Activations Density 0.003%

    No Known Activations