© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68212
    Prev
    Next
    INDEX
    Explanations

    justices and names

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

    This neuron activates on structural metadata and heading words that introduce formal document sections (e.g. schedule notices in obituaries or lists of judicial officers in court opinions).

    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
     Nieren
    -1.01
    的价格
    -0.90
     وغير
    -0.85
     přímo
    -0.81
    uste
    -0.81
     меры
    -0.81
    aporte
    -0.81
     that
    -0.81
    !="")
    -0.81
     ścian
    -0.80
    POSITIVE LOGITS
     at
    1.26
     trưng
    1.06
     allowing
    1.03
    KEYCODE
    1.02
     Thursday
    1.02
     allow
    1.01
     fera
    1.00
     éves
    0.98
     Monday
    0.98
     Tuesday
    0.97
    Activations Density 0.000%

    No Known Activations