© 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. 23502
    Prev
    Next
    INDEX
    Explanations

    parental rights visitation relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     precede
    -0.85
     widows
    -0.79
     wives
    -0.78
     cordless
    -0.78
     clemen
    -0.75
    жима
    -0.74
     sits
    -0.73
     OMB
    -0.72
     infallible
    -0.72
    irma
    -0.69
    POSITIVE LOGITS
     parent
    1.23
     parents
    1.06
     Eltern
    1.05
    parent
    0.98
    PARENT
    0.93
    Parent
    0.91
     Parent
    0.90
     concreta
    0.87
    +":
    0.86
     significativa
    0.85
    Activations Density 0.008%

    No Known Activations