© 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. 116570
    Prev
    Next
    INDEX
    Explanations

    child abuse and neglect

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

    This neuron detects references to child maltreatment or abuse (e.g. “child maltreatment,” “child abuse,” and related protective‐services terminology).

    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
    Introdução
    -0.82
    Tracing
    -0.71
     发表于
    -0.71
    Symb
    -0.67
    virano
    -0.67
    PHE
    -0.66
    槎
    -0.66
    Filme
    -0.66
     levert
    -0.66
    Patient
    -0.65
    POSITIVE LOGITS
     families
    0.94
     neglect
    0.90
     family
    0.87
     safety
    0.86
     allegations
    0.84
     protective
    0.82
     CPS
    0.81
    protective
    0.81
     mal
    0.79
     mandated
    0.79
    Activations Density 0.025%

    No Known Activations