© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    broken or damaged things

    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
     sociala
    -1.56
     förslag
    -1.56
    いいのか
    -1.51
    EN
    -1.51
     timmar
    -1.45
    ية
    -1.42
    delmi
    -1.40
     sidor
    -1.38
     frågor
    -1.34
    发展的
    -1.34
    POSITIVE LOGITS
    ediakan
    1.56
     Terkait
    1.55
    elesaikan
    1.48
     Tujuan
    1.41
     edisi
    1.40
     オン
    1.33
     Kemudian
    1.30
     dijadikan
    1.29
     キッズ
    1.28
     Lainnya
    1.28
    Activations Density 0.079%

    No Known Activations