© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111004
    Prev
    Next
    INDEX
    Explanations

    operations and processes

    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
     and
    -2.84
    0
    -2.34
    }}$
    -2.02
     consisting
    -2.00
    子的
    -1.99
     汽車
    -1.98
    ⡪
    -1.96
    ници
    -1.84
     ブルゾン
    -1.79
     provinciale
    -1.78
    POSITIVE LOGITS
     
    2.33
    es
    1.95
     wasnt
    1.93
     "[
    1.89
    %;
    1.84
    vantaged
    1.82
    外观
    1.81
     Could
    1.80
     solteiro
    1.80
     We
    1.77
    Activations Density 0.087%

    No Known Activations