© 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. 11499
    Prev
    Next
    INDEX
    Explanations

    questions about possibility or implementation

    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
    -2.17
    
    -2.16
    ſelves
    -2.14
    龉
    -2.06
     aprobó
    -1.88
    喾
    -1.88
    齶
    -1.88
     Они
    -1.80
     "?"
    -1.77
     ","
    -1.77
    POSITIVE LOGITS
    6
    2.05
     these
    2.03
     this
    1.99
    2
    1.83
     theres
    1.75
     those
    1.71
     makes
    1.70
     spurred
    1.69
     it
    1.68
     your
    1.64
    Activations Density 0.005%

    No Known Activations