© 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. 48527
    Prev
    Next
    INDEX
    Explanations

    estate planning

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

    This neuron detects text discussing preparing a will or estate‐planning matters.

    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
    Inspect
    -0.93
    orer
    -0.85
     narod
    -0.81
    ovatel
    -0.80
    mimeType
    -0.79
    Nova
    -0.78
    }-*/;
    -0.77
    }=
    -0.76
     Inspect
    -0.76
    Demo
    -0.74
    POSITIVE LOGITS
     estate
    2.89
     Estate
    2.38
    Estate
    2.22
    estate
    1.97
     planning
    1.71
     ESTATE
    1.63
     estates
    1.59
     probate
    1.51
     Planning
    1.46
     wills
    1.35
    Activations Density 0.038%

    No Known Activations