© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10383
    Prev
    Next
    INDEX
    Explanations

    legal advice and documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Christy
    1.01
     పంట
    0.97
     detergent
    0.94
    mpi
    0.92
    嵊
    0.91
     nhi
    0.90
     Küchen
    0.90
     cereals
    0.89
     Pitt
    0.88
    穀
    0.87
    POSITIVE LOGITS
     Legal
    3.78
    Legal
    3.61
     lawyers
    3.61
     legal
    3.57
     Lawyer
    3.54
     LEGAL
    3.50
    legal
    3.44
     Lawyers
    3.40
     lawyer
    3.37
    法律
    3.34
    Activations Density 0.540%

    No Known Activations