© 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. 22-GEMMASCOPE-RES-131K
    7. 69163
    Prev
    Next
    INDEX
    Explanations

    chrome browser

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

    The neuron fires on occurrences of the word “chrome” (i.e. mentions of the Chrome browser).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     you
    -2.45
    谖
    -2.34
     know
    -2.31
    ’?
    -2.19
    pagnols
    -2.11
     was
    -2.09
    </h3>
    -2.02
    퐼
    -1.99
     murderers
    -1.98
    学会
    -1.98
    POSITIVE LOGITS
     Allgemeinen
    2.33
     zusätzliche
    2.19
     másik
    2.09
     avaient
    2.09
    щита
    2.06
    犄
    2.06
    </b>
    2.00
     variedade
    1.98
    ‌‌
    1.98
     són
    1.97
    Activations Density 0.028%

    No Known Activations