© 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. 129224
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

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

    The main thing this neuron does is detect references to UI pop‐up components or dialogs (e.g. “dialog,” “form,” “Tips,” “pop…up,” “window”).

    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
     it
    -1.29
     они
    -1.23
    toir
    -1.17
     烟
    -1.15
    cte
    -1.13
    levant
    -1.13
     astonishing
    -1.12
    kates
    -1.11
    ᑭ
    -1.10
     camiones
    -1.09
    POSITIVE LOGITS
    Spécifications
    1.10
     Tempor
    1.07
    rectal
    1.03
     knew
    1.03
     method
    1.03
     hereby
    1.02
    Достоинства
    1.02
     would
    1.02
    ppsala
    1.01
    ｻ
    1.01
    Activations Density 0.111%

    No Known Activations