© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101016
    Prev
    Next
    INDEX
    Explanations

    Po followed by a word

    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
    Negative Logits
    :{
    -1.54
    chloride
    -1.48
     sanitario
    -1.38
     человека
    -1.31
     pedir
    -1.28
     ？
    -1.26
     OCTOBER
    -1.25
     SAVINGS
    -1.24
     sonre
    -1.23
    𝐫
    -1.23
    POSITIVE LOGITS
     then
    2.14
     also
    1.95
    )
    1.74
    ],
    1.55
     quaisquer
    1.48
     another
    1.41
    ,
    1.41
     of
    1.41
     for
    1.39
    ",
    1.34
    Activations Density 0.067%

    No Known Activations