© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73
    Prev
    Next
    INDEX
    Explanations

    court case citations

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

    This neuron fires on numeric tokens and formatted numeric sequences (e.g., docket numbers, dates, or multi‐digit case reference strings).

    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
     puissiez
    -0.93
    ようになりました
    -0.90
    のかも
    -0.88
     if
    -0.86
    ьере
    -0.85
    ##############
    -0.85
     contribute
    -0.85
     share
    -0.85
     what
    -0.85
     initiatives
    -0.85
    POSITIVE LOGITS
    competent
    1.13
    visi
    1.12
     JEN
    1.10
     teknis
    1.10
     detalj
    1.09
    ಇ
    1.05
     odol
    1.03
    憷
    1.03
     فہرست
    1.01
     vinaigre
    1.01
    Activations Density 0.061%

    No Known Activations