© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15391
    Prev
    Next
    INDEX
    Explanations

    estate planning probate

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     பயணிகள்
    0.64
     Liefer
    0.62
     оте
    0.58
     अभ्यर्थ
    0.55
    🍟
    0.55
    徕
    0.54
     Recruitment
    0.53
    केंसी
    0.52
     વરસાદ
    0.52
     腰
    0.52
    POSITIVE LOGITS
     probate
    2.00
     Probate
    1.78
     testamentary
    1.77
     executors
    1.76
     estate
    1.73
     executor
    1.69
     intestate
    1.64
     Executor
    1.63
     Executors
    1.60
     testator
    1.59
    Activations Density 0.137%

    No Known Activations