© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83863
    Prev
    Next
    INDEX
    Explanations

    risk of negative outcomes

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

    The neuron is a high‐precision detector for the word “risk” (especially in the phrase “risk of …”) in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Either
    -1.75
    problema
    -1.66
     either
    -1.65
     möglicherweise
    -1.60
    Ultimately
    -1.60
     Ultimately
    -1.58
    either
    -1.58
     Possibly
    -1.55
     huidige
    -1.53
    tamaris
    -1.51
    POSITIVE LOGITS
     of
    2.42
     which
    1.56
    f
    1.48
    ）
    1.48
     martes
    1.47
    如
    1.41
     avec
    1.38
    ḵ
    1.38
    >
    1.38
     empat
    1.37
    Activations Density 0.013%

    No Known Activations