© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    racing conference, kill pen, metal on

    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
     behulp
    -1.58
     omtrent
    -1.56
    dată
    -1.56
     perioden
    -1.54
    ༔
    -1.52
    ategorie
    -1.52
    áció
    -1.51
     grupper
    -1.50
    幛
    -1.48
    ଢ
    -1.47
    POSITIVE LOGITS
     then
    1.61
     recipiente
    1.60
     time
    1.51
     in
    1.47
     fritas
    1.37
    }(
    1.36
    كثر
    1.36
     tehdä
    1.34
     vegano
    1.33
     ingrediente
    1.31
    Activations Density 0.147%

    No Known Activations