© 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. 127194
    Prev
    Next
    INDEX
    Explanations

    browse

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

    The neuron activates on words related to “browse” (including “Browse,” “browse,” “browsing,” and “Browser”), i.e. navigation or listing actions.

    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
     髪型
    -2.63
    觔
    -2.55
    𖥧
    -2.53
     Ersten
    -2.41
    jenigen
    -2.39
    鸲
    -2.39
     může
    -2.38
     seleccionamos
    -2.34
    ával
    -2.33
     prevenir
    -2.30
    POSITIVE LOGITS
    able
    2.72
     japoneses
    2.52
    ."
    2.41
    Hanya
    2.39
    of
    2.34
     italianos
    2.33
     uplifting
    2.31
    𝙒
    2.30
    性价比
    2.30
     europeos
    2.30
    Activations Density 0.004%

    No Known Activations