© 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. 129824
    Prev
    Next
    INDEX
    Explanations

    defining object properties and getters/setters

    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
     anybody
    -1.81
     anyone
    -1.77
     any
    -1.52
    );
    -1.52
     quaisquer
    -1.50
    Poetry
    -1.43
    any
    -1.38
    鴆
    -1.38
     qualsiasi
    -1.37
    anyone
    -1.34
    POSITIVE LOGITS
    ’
    1.74
     просто
    1.44
    '
    1.41
     new
    1.38
     recherchez
    1.36
    1.34
     Keeping
    1.33
     |\
    1.31
     noteworthy
    1.29
     weird
    1.27
    Activations Density 0.013%
    No Known Activations