© 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. 9296
    Prev
    Next
    INDEX
    Explanations

    Formatting characters

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

    This neuron detects long runs of repeated punctuation characters (like ####…, ****…, ====…, ——, ___) used as decorative banner or separator lines in comments.

    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
     goog
    -1.01
    ซื้อ
    -0.97
     automati
    -0.96
     inverte
    -0.96
     τῶν
    -0.95
    即購入
    -0.93
     modeller
    -0.91
     Souver
    -0.91
     resili
    -0.90
     journalistes
    -0.90
    POSITIVE LOGITS
     dårlig
    1.08
    щенный
    1.04
    修为
    1.03
    НАЯ
    1.02
     réduire
    1.02
    眼中
    1.02
     hielt
    1.00
    stereotype
    0.98
    </i>
    0.98
     weihnachten
    0.97
    Activations Density 0.015%

    No Known Activations