© 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. 99416
    Prev
    Next
    INDEX
    Explanations

    money, payments, donors, contributions

    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
    ׇ
    -1.75
     now
    -1.49
     گیاه
    -1.41
     chré
    -1.33
     tomba
    -1.30
     trying
    -1.28
     still
    -1.28
     овощи
    -1.21
    rifugal
    -1.21
    ⾦
    -1.18
    POSITIVE LOGITS
     selben
    1.30
    kwij
    1.21
    including
    1.19
     are
    1.18
     gleichen
    1.16
    ֶּ
    1.16
     beschreibt
    1.14
     späteren
    1.14
     Webseite
    1.13
    zelfde
    1.12
    Activations Density 0.095%

    No Known Activations