© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87155
    Prev
    Next
    INDEX
    Explanations

    financial and surgical risk management

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

    The neuron is activated by language describing adjustments or control of financial risk exposures (e.g. reducing, weighting, balancing 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
    🔔
    -0.83
    龅
    -0.82
    olle
    -0.81
     Ruh
    -0.79
    XYGEN
    -0.78
    阵法
    -0.78
     diagno
    -0.77
     Fj
    -0.75
    ναν
    -0.75
     falschen
    -0.75
    POSITIVE LOGITS
     risk
    7.38
     risks
    6.00
    risk
    5.63
     Risk
    5.56
    Risk
    5.28
     RISK
    4.56
     Risks
    4.53
    风险
    4.41
    risks
    4.34
    RISK
    4.22
    Activations Density 0.063%

    No Known Activations