© 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. 128823
    Prev
    Next
    INDEX
    Explanations

    copyright infringement and impingement

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

    The neuron specializes in spotting words that end with the “ingement” suffix (e.g. “infringement,” “impingement”).

    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
    ᥬ
    -2.77
    킁
    -2.66
    姈
    -2.39
    猻
    -2.38
    or
    -2.36
     撮っ
    -2.33
    ☫
    -2.30
     laisse
    -2.28
    0
    -2.27
    癭
    -2.20
    POSITIVE LOGITS
    ).
    3.41
    潆
    2.95
     gleiche
    2.70
    沕
    2.58
    sudadera
    2.48
     übri
    2.41
    ⬮
    2.22
     vorhand
    2.20
     Ради
    2.20
    ต่างๆ
    2.14
    Activations Density 0.003%

    No Known Activations