© 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. 103564
    Prev
    Next
    INDEX
    Explanations

    equal treatment and adherence to standards

    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
     to
    -1.69
     obligación
    -1.64
     già
    -1.60
    )}$
    -1.52
     lijkt
    -1.51
     namens
    -1.51
     legislación
    -1.50
     hipótesis
    -1.49
    ḿ
    -1.48
     manifestación
    -1.46
    POSITIVE LOGITS
     first
    1.79
    There
    1.77
    喽
    1.66
     high
    1.65
     other
    1.55
    Other
    1.54
     all
    1.52
    there
    1.47
    Ἔ
    1.46
     one
    1.42
    Activations Density 0.087%

    No Known Activations