© 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. 113220
    Prev
    Next
    INDEX
    Explanations

    browse content

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

    The neuron activates on words and forms that denote browsing or navigating content (e.g. “browse,” “browsed,” “browsing,” “explore,” etc.).

    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
     Those
    -1.72
    Ꮉ
    -1.40
     Sadly
    -1.38
     Notably
    -1.36
    那些
    -1.34
    Those
    -1.34
     suuri
    -1.34
     Perhaps
    -1.32
    ローチ
    -1.29
     Importantly
    -1.28
    POSITIVE LOGITS
    螣
    1.51
     organes
    1.45
     señ
    1.45
    鴣
    1.43
    芣
    1.42
    htt
    1.41
    蹰
    1.37
    taciones
    1.36
     tenues
    1.35
     folhe
    1.32
    Activations Density 0.050%

    No Known Activations