© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58754
    Prev
    Next
    INDEX
    Explanations

    Supreme Court appeals

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

    The neuron selectively fires on formal legal citations—statute names (e.g. “Appellate,” “Jurisdiction,” “Act”) and case‐report references (years, bracketed 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_34/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
    NTP
    -0.81
     efic
    -0.74
    ựa
    -0.66
    뤄
    -0.64
    ife
    -0.64
    eniendo
    -0.64
     کف
    -0.64
     apropi
    -0.63
     شد
    -0.63
     год
    -0.63
    POSITIVE LOGITS
    Appeal
    1.00
     appeal
    0.98
     Appeal
    0.94
    appeal
    0.89
     appeals
    0.89
     unanimously
    0.84
     unanimous
    0.82
    Climbing
    0.79
    ByUrl
    0.78
     labdar
    0.78
    Activations Density 0.070%

    No Known Activations