© 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. 91522
    Prev
    Next
    INDEX
    Explanations

    injury law firms and lawyers

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

    The main thing this neuron does is detect language related to personal injury law practice (e.g., wrongful death and injury case terminology).

    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
     parity
    -0.77
    amu
    -0.74
     Unido
    -0.73
     Threat
    -0.73
     vitae
    -0.73
    threat
    -0.72
     PROBLEM
    -0.72
    Cyfeiriadau
    -0.71
    Prob
    -0.71
    Array
    -0.71
    POSITIVE LOGITS
     injury
    2.45
     injured
    2.05
     injuries
    1.96
     Injury
    1.95
    Injury
    1.83
    injury
    1.78
     Injuries
    1.74
     accident
    1.72
     Injured
    1.65
    Injured
    1.61
    Activations Density 0.048%

    No Known Activations