© 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. 36525
    Prev
    Next
    INDEX
    Explanations

    academic address formatting

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

    The neuron strongly activates on backslash-u escape sequences (e.g. “\u000a”) in code.

    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
     on
    -1.23
    <0xA3>
    -1.21
    を
    -1.08
    時間は
    -1.04
    が
    -1.02
    などを
    -1.00
    で
    -0.99
    も
    -0.97
    があり
    -0.97
    けどね
    -0.96
    POSITIVE LOGITS
    感じで
    1.16
    様な
    1.12
    感じが
    1.09
     dû
    1.07
     imediatamente
    1.07
    ございません
    1.05
    の基本
    1.05
    遢
    1.03
    為に
    1.03
    ኹ
    1.02
    Activations Density 0.064%

    No Known Activations