© 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. 10-GEMMASCOPE-RES-131K
    7. 44803
    Prev
    Next
    INDEX
    Explanations

    justify expenditure or behavior

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

    The neuron strongly activates on the word “justify” (and its noun form “justification”).

    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
     to
    -2.78
    щита
    -2.58
     akin
    -2.36
     Now
    -2.30
     ''
    -2.30
    %"
    -2.22
     серия
    -2.20
     The
    -2.20
     be
    -2.14
     pueden
    -2.09
    POSITIVE LOGITS
    1
    3.14
    s
    2.91
    You
    2.56
    But
    2.34
    旁邊
    2.30
    e
    2.23
    糶
    2.19
    0
    2.17
    時間に
    2.14
    d
    2.13
    Activations Density 0.003%

    No Known Activations