© 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. 25285
    Prev
    Next
    INDEX
    Explanations

    fathers and parents

    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_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
    <
    -1.08
     when
    -1.08
    !!!!!
    -1.02
    പ്
    -0.96
     íntima
    -0.95
    窗
    -0.93
    !!!!
    -0.93
     people
    -0.91
    łko
    -0.91
    .......
    -0.89
    POSITIVE LOGITS
     parenting
    1.91
     parents
    1.88
     father
    1.83
     parental
    1.83
     parent
    1.66
     family
    1.47
    Parents
    1.39
     genitori
    1.39
    parental
    1.38
     parenthood
    1.37
    Activations Density 0.044%

    No Known Activations