© 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. 10-GEMMASCOPE-RES-131K
    7. 72636
    Prev
    Next
    INDEX
    Explanations

    eldest brother, son, daughter

    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_10/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
    歺
    -2.67
    麃
    -2.64
    蚡
    -2.55
     墊
    -2.45
    ᠁
    -2.31
    扨
    -2.27
    癭
    -2.27
    ຝ
    -2.27
    蟶
    -2.27
    峮
    -2.25
    POSITIVE LOGITS
     On
    2.78
    On
    2.41
    ons
    2.41
     после
    2.34
     здесь
    2.34
     During
    2.27
    他在
    2.27
    琑
    2.25
     realizzato
    2.22
     troublesome
    2.20
    Activations Density 0.002%

    No Known Activations