© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129444
    Prev
    Next
    INDEX
    Explanations

    Angular modules and components

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

    The neuron fires on code references to opening or creating modal dialog instances (e.g. “$modal.open”, “ModalInstance”).

    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
    (
    -1.56
     Vielzahl
    -1.39
     trabajan
    -1.32
    g
    -1.30
    这下
    -1.30
     funcionan
    -1.27
     myriad
    -1.27
    f
    -1.26
     небольшой
    -1.26
     distintos
    -1.26
    POSITIVE LOGITS
    ~~~~
    1.42
    嫗
    1.33
     OTTO
    1.29
    hibits
    1.27
    ayı
    1.23
     ultima
    1.22
    kań
    1.21
    ……」
    1.20
     atitude
    1.20
    şört
    1.17
    Activations Density 0.008%

    No Known Activations