© 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. 478
    Prev
    Next
    INDEX
    Explanations

    custody and visitation

    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
     přij
    -0.88
     ratification
    -0.87
     castel
    -0.82
     "$(
    -0.80
    ртка
    -0.77
     }}(\
    -0.77
    })-\
    -0.77
    getNombre
    -0.75
     Nachfolger
    -0.75
    ród
    -0.74
    POSITIVE LOGITS
     custody
    3.45
     Custody
    2.22
    Cust
    2.02
    cust
    2.02
     visitation
    1.84
     custodial
    1.78
    Visitation
    1.72
     custodia
    1.63
    custo
    1.55
     parenting
    1.51
    Activations Density 0.037%

    No Known Activations