© 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. 22-GEMMASCOPE-RES-131K
    7. 72826
    Prev
    Next
    INDEX
    Explanations

    legal citations and acts

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

    The neuron activates on numeric tokens in legal citations and references (e.g., section numbers, years, volume and page numbers).

    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
     fufficient
    -1.21
    faden
    -1.16
     स्क्रीन
    -1.14
     fhort
    -1.13
     bilder
    -1.12
    FORME
    -1.12
    logOut
    -1.11
     ezek
    -1.09
    convertView
    -1.08
    bör
    -1.08
    POSITIVE LOGITS
     ändert
    1.55
    民众
    1.38
     changes
    1.33
    hysema
    1.30
     Wartawan
    1.27
    选举
    1.22
     السياس
    1.22
     правительства
    1.21
    ranslated
    1.15
     additions
    1.13
    Activations Density 0.013%

    No Known Activations