© 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. 102557
    Prev
    Next
    INDEX
    Explanations

    children, sons, daughters, infants

    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
     and
    -1.80
    ed
    -1.35
     my
    -1.34
    ,
    -1.28
     at
    -1.27
    8
    -1.21
     also
    -1.20
    1
    -1.17
     it
    -1.17
    ↵
    -1.17
    POSITIVE LOGITS
    关于
    1.55
    Antes
    1.42
     jų
    1.38
    ERICAN
    1.37
    Cuando
    1.37
     mají
    1.36
    När
    1.35
     ganska
    1.34
     cuando
    1.31
     långt
    1.30
    Activations Density 0.043%

    No Known Activations