© 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. 83799
    Prev
    Next
    INDEX
    Explanations

    election coordinator, community board, thermal tolerance, clinical evaluation

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

    The neuron consistently fires on the formal header elements of legal opinions—court names, docket numbers, parties, dates, and judge attributions.

    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
     regularly
    -0.80
     much
    -0.74
     although
    -0.73
     specific
    -0.72
     too
    -0.71
    ポイントは
    -0.70
     ApiClient
    -0.69
     inmediata
    -0.68
     consistently
    -0.67
     important
    -0.66
    POSITIVE LOGITS
    SetFont
    0.94
    tilt
    0.84
    anud
    0.83
     macrop
    0.81
     Kana
    0.80
    蜍
    0.80
     rgb
    0.80
     KING
    0.79
     Coaster
    0.78
    ירים
    0.78
    Activations Density 0.047%

    No Known Activations