© 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. 10-GEMMASCOPE-RES-131K
    4. 75425
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

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

    The neuron consistently activates on occurrences of the word “courts.”

    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
     
    -2.23
     Extremely
    -2.19
    Surprisingly
    -2.13
    Now
    -2.13
    Recently
    -2.11
     scary
    -2.09
     Seriously
    -2.09
    Interestingly
    -2.08
     Honestly
    -2.08
     Recently
    -2.08
    POSITIVE LOGITS
    s
    3.86
    to
    3.33
    p
    3.23
    b
    3.17
    m
    3.13
    k
    3.03
    n
    2.97
     are
    2.91
    c
    2.88
    h
    2.80
    Activations Density 0.006%

    No Known Activations