© 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. 102764
    Prev
    Next
    INDEX
    Explanations

    potential risks or opportunities

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

    This neuron activates on the word “potential” (as in “potential X”).

    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
    嵙
    -1.56
     berserk
    -1.48
    CÓ
    -1.48
     mentales
    -1.47
     welk
    -1.45
     cocky
    -1.41
    𝗴
    -1.38
     décès
    -1.37
     kemudian
    -1.36
     sebagainya
    -1.36
    POSITIVE LOGITS
     unangemessene
    1.76
    a
    1.66
    ୌ
    1.64
     was
    1.61
     a
    1.55
     cartaz
    1.51
     pulseira
    1.50
     хочет
    1.46
    емость
    1.46
     unicórnio
    1.43
    Activations Density 0.027%

    No Known Activations