© 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. 10-GEMMASCOPE-RES-131K
    7. 101051
    Prev
    Next
    INDEX
    Explanations

    clients and customers

    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
    They
    -1.31
    !”
    -1.31
    Они
    -1.30
     only
    -1.30
    Опыт
    -1.28
    ݮ
    -1.27
    슨
    -1.26
    Жизнь
    -1.25
    Только
    -1.24
     faktiskt
    -1.24
    POSITIVE LOGITS
     zilver
    1.47
     nadru
    1.43
     tutte
    1.38
    dubai
    1.38
     juiste
    1.36
    Univ
    1.35
     oorspron
    1.34
    ᯾
    1.33
     grijs
    1.33
    <.
    1.33
    Activations Density 0.035%

    No Known Activations