© 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. 34-GEMMASCOPE-RES-131K
    7. 98632
    Prev
    Next
    INDEX
    Explanations

    legal cases and appellants

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

    The neuron detects the structured header information of legal case opinions—i.e. the court citations, docket numbers, dates, judge names, and related metadata at the top of each decision.

    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
     tarjeta
    -0.84
     запре
    -0.76
     sweetened
    -0.74
    CreateUser
    -0.73
    Svar
    -0.73
    gloss
    -0.72
    Drilling
    -0.72
    imon
    -0.71
    Mandy
    -0.71
     montaña
    -0.70
    POSITIVE LOGITS
    Birmingham
    0.87
     Birmingham
    0.85
    Alabama
    0.76
     Value
    0.73
    Value
    0.72
    Batch
    0.71
    Tennessee
    0.70
    ALD
    0.69
     Bell
    0.68
    Bell
    0.68
    Activations Density 0.044%

    No Known Activations