© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77013
    Prev
    Next
    INDEX
    Explanations

    incident

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

    This neuron fires on mentions of (news) “incidents” or similar event‐report phrases (e.g. the word “incident” and related reporting terms).

    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
    бол
    -0.91
    мне
    -0.88
    жко
    -0.85
     تغی
    -0.81
    ingos
    -0.79
     pembunuhan
    -0.79
    quées
    -0.78
    byes
    -0.78
    -0.77
     killers
    -0.77
    POSITIVE LOGITS
     incident
    6.31
     incidents
    4.50
    incident
    4.03
     Incident
    3.86
    事件
    3.31
     incidence
    3.28
    Incident
    3.19
     incidente
    3.09
     Incidents
    2.91
     event
    2.89
    Activations Density 0.102%

    No Known Activations