© 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. 10-GEMMASCOPE-RES-131K
    7. 13382
    Prev
    Next
    INDEX
    Explanations

    mortgage

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

    The neuron detects occurrences of the word “mortgage” (including its compounds and inflections).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    砹
    -2.47
    rowable
    -2.45
    埽
    -2.45
    泐
    -2.45
    樒
    -2.39
    鯪
    -2.36
     pertenec
    -2.36
    佧
    -2.25
    ޗ
    -2.22
    ۔
    -2.20
    POSITIVE LOGITS
    ↵
    3.69
    Y
    3.13
    H
    2.91
    L
    2.50
    d
    2.11
    N
    2.02
    P
    1.99
    J
    1.96
     שנים
    1.93
    T
    1.91
    Activations Density 0.012%

    No Known Activations