© 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. 48347
    Prev
    Next
    INDEX
    Explanations

    shorter duration or distance

    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
    {
    -3.00
    哎呀
    -2.36
    thenburg
    -2.36
    sandalia
    -2.33
    
    -2.30
    
    -2.16
     astute
    -2.08
    風の
    -2.08
     การ์ตูน
    -2.08
    鴴
    -2.03
    POSITIVE LOGITS
    that
    2.77
    ان
    2.67
    x
    2.61
    м
    2.59
    1
    2.53
    ist
    2.48
    р
    2.47
    3
    2.44
    an
    2.42
    4
    2.38
    Activations Density 0.003%

    No Known Activations