© 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. 119520
    Prev
    Next
    INDEX
    Explanations

    Yorkshire terrier, family, Cup

    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
    {
    -2.88
    砹
    -2.78
    ).
    -2.56
    t
    -2.45
    *
    -2.36
    푆
    -2.34
    躂
    -2.33
    h
    -2.25
    
    -2.25
    m
    -2.23
    POSITIVE LOGITS
    玊
    2.59
    風に
    2.09
    事も
    2.03
     facilitator
    2.00
     vivía
    2.00
    们的
    1.99
    ly
    1.99
    在下
    1.98
     jenem
    1.98
     wob
    1.97
    Activations Density 0.002%

    No Known Activations