© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31652
    Prev
    Next
    INDEX
    Explanations

    OJ Simpson trial

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

    The neuron is on the lookout for numbers—digits used in legal‐document contexts (e.g. years, docket and case citations).

    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
     Seton
    -0.76
     McCabe
    -0.74
     Gaulle
    -0.72
    CVE
    -0.69
    Sheldon
    -0.68
     Patch
    -0.68
    covi
    -0.67
     持つ
    -0.66
    Cyclo
    -0.66
     McGovern
    -0.66
    POSITIVE LOGITS
     OJ
    1.48
     Simpson
    1.38
     Juice
    1.20
    Simpson
    1.15
     Goldman
    1.09
     Nicole
    1.06
     Bronco
    1.01
    OJ
    0.98
     Fuhr
    0.94
    Nicole
    0.93
    Activations Density 0.015%

    No Known Activations