© 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. 34-GEMMASCOPE-RES-131K
    7. 82671
    Prev
    Next
    INDEX
    Explanations

    mangoes or Windows Phone codename Mango

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

    The neuron specializes in spotting occurrences of the word “mango” (in any form or context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     lavender
    -0.85
    indelijk
    -0.82
    FIS
    -0.81
    tun
    -0.80
    hnia
    -0.79
    LEP
    -0.76
    Immediate
    -0.75
     Ե
    -0.75
     fluor
    -0.73
    ⏜
    -0.73
    POSITIVE LOGITS
    🥭
    1.33
     Mango
    0.89
    Mango
    0.87
     mango
    0.86
    mango
    0.79
     mang
    0.76
     nectar
    0.75
     prévue
    0.74
     ман
    0.73
    鹦
    0.73
    Activations Density 0.013%

    No Known Activations