© 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. 106757
    Prev
    Next
    INDEX
    Explanations

    increased risk or likelihood

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

    The neuron flags mentions of disease‐ or health‐related risk, especially words indicating increased risk.

    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
    Ofer
    -0.82
    kde
    -0.73
     VoIP
    -0.71
    ic
    -0.70
     могло
    -0.70
    前言
    -0.69
    ότη
    -0.68
     Гон
    -0.68
    ূ
    -0.68
     ${({
    -0.67
    POSITIVE LOGITS
     risk
    3.56
    Risk
    2.70
    risk
    2.69
     Risk
    2.58
     risks
    2.52
     RISK
    2.31
     riesgo
    2.20
    风险
    2.11
     Risks
    1.97
    RISK
    1.93
    Activations Density 0.199%

    No Known Activations