© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108963
    Prev
    Next
    INDEX
    Explanations

    numbers of children

    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
    頜
    -0.98
     ベッド
    -0.96
    jalá
    -0.95
    这些
    -0.94
    bộ
    -0.94
    ród
    -0.94
    髫
    -0.93
    diseases
    -0.93
    zufügen
    -0.91
    赤ちゃん
    -0.88
    POSITIVE LOGITS
     children
    2.27
     daughter
    2.16
     daughters
    2.08
     son
    1.97
     sons
    1.91
     two
    1.42
     three
    1.39
     brother
    1.34
     sister
    1.25
    children
    1.20
    Activations Density 0.001%

    No Known Activations