© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71804
    Prev
    Next
    INDEX
    Explanations

    restructure, reseller, resection

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

    The neuron responds to any token containing the substring “structur” (e.g. restructure/restructuring/destructuring).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     If
    -2.78
    iſter
    -2.61
     squadre
    -2.45
     But
    -2.39
    𖣘
    -2.38
    鏐
    -2.36
     sebelum
    -2.34
    -
    -2.33
    總是
    -2.27
     Leuten
    -2.22
    POSITIVE LOGITS
     is
    2.59
    ↵
    2.44
    拳头
    2.39
    哔
    2.38
    
    2.30
    ဴ
    2.19
    
    2.14
    芣
    2.14
    栒
    2.13
    但他
    2.11
    Activations Density 0.004%

    No Known Activations