© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27121
    Prev
    Next
    INDEX
    Explanations

    interjections and affirmations

    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_22/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
    -1.90
    PENDAHULUAN
    -1.77
     וכן
    -1.33
    ỡng
    -1.28
     Besonder
    -1.27
    inglés
    -1.23
    توضیحات
    -1.23
    Клуб
    -1.22
     PUSTAKA
    -1.22
    Биография
    -1.20
    POSITIVE LOGITS
    ,
    1.83
    !
    1.48
     you
    1.46
     they
    1.35
     oluyor
    1.34
    .
    1.34
    ことはありません
    1.27
     carregar
    1.22
    ’
    1.21
     vaan
    1.20
    Activations Density 0.013%

    No Known Activations