© 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. 84562
    Prev
    Next
    INDEX
    Explanations

    litigation and Lindsey Graham

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

    The neuron fires on occurrences of the word “litigation” (in any case or context).

    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
    bluza
    -2.50
    慊
    -2.45
    嗩
    -2.41
    dzić
    -2.38
    嫆
    -2.31
    érées
    -2.27
    رى
    -2.23
    Ⲉ
    -2.22
     ваше
    -2.19
     jangan
    -2.09
    POSITIVE LOGITS
    i
    4.00
    ta
    2.89
    ,“
    2.48
    </i>
    2.44
    
    2.38
    呖
    2.38
    та
    2.31
    ский
    2.27
    :”
    2.27
    <
    2.25
    Activations Density 0.001%

    No Known Activations