© 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. 22-GEMMASCOPE-RES-131K
    7. 72985
    Prev
    Next
    INDEX
    Explanations

    estate of deceased or minors

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

    The neuron activates on legal‐estate terminology, especially words in “Estate of…Deceased” or related probate phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    rsiniz
    -1.23
    amna
    -1.13
    ↵↵↵↵↵↵↵
    -1.07
     блюдо
    -1.05
    acağı
    -1.05
    cún
    -1.02
     those
    -1.01
    ↵↵↵↵↵↵↵↵↵
    -1.01
    +=(
    -1.01
    ↵↵↵↵↵↵
    -0.99
    POSITIVE LOGITS
    Koordin
    1.29
    っていきます
    1.26
     насеља
    1.26
    っております
    1.23
     државе
    1.21
    𝟑
    1.20
     vacacionales
    1.20
     salvajes
    1.20
     estadounidenses
    1.19
    阅读原文
    1.17
    Activations Density 0.002%

    No Known Activations