© 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. 79725
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation

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

    The neuron fires on prominent, information-bearing words—especially formal news-style discourse markers, key nouns, and past‐tense or nominalized verbs that signal important developments.

    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
    writeField
    -0.90
    って思
    -0.90
    Ņ
    -0.90
     our
    -0.87
     ilman
    -0.86
    Podob
    -0.86
     your
    -0.85
     насеља
    -0.83
    。“
    -0.82
    Menurut
    -0.82
    POSITIVE LOGITS
     indeed
    1.00
    🔅
    0.99
    時間で
    0.98
     agregó
    0.97
     espacios
    0.96
     fourn
    0.94
    っちゃう
    0.94
    Indeed
    0.93
     Indeed
    0.93
    やかに
    0.92
    Activations Density 0.027%

    No Known Activations