© 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. 73321
    Prev
    Next
    INDEX
    Explanations

    adjective after a/the

    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
    Ꭻ
    -1.43
    海鮮
    -1.35
     potuto
    -1.34
     industrias
    -1.34
    Other
    -1.34
    諜
    -1.33
    してた
    -1.31
    ꨄ
    -1.30
     fossero
    -1.30
     erweitert
    -1.29
    POSITIVE LOGITS
     are
    1.76
     secondes
    1.40
    𝟏
    1.32
     nho
    1.29
     upor
    1.29
    sometimes
    1.25
     Nowy
    1.25
     couverture
    1.22
     Ś
    1.21
     když
    1.21
    Activations Density 0.027%

    No Known Activations