© 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. 22-GEMMASCOPE-RES-131K
    7. 72146
    Prev
    Next
    INDEX
    Explanations

    child protective services termination

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

    The neuron strongly activates on references to child welfare and protective‐services contexts—terms like “Children’s Services,” “child protective services,” “child maltreatment,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     '-';
    -1.24
     saab
    -1.16
     nina
    -1.16
     generale
    -1.14
     lidl
    -1.12
     安装
    -1.12
    v
    -1.12
    奬
    -1.11
    ,
    -1.09
    ul
    -1.08
    POSITIVE LOGITS
     child
    1.84
     children
    1.69
    เด็ก
    1.37
    (ﾟ
    1.36
     děti
    1.32
     dítě
    1.32
     ragazza
    1.31
     casas
    1.26
     services
    1.24
    nungs
    1.23
    Activations Density 0.053%

    No Known Activations