© 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. 34-GEMMASCOPE-RES-131K
    7. 55767
    Prev
    Next
    INDEX
    Explanations

    NOW, followed by date

    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_34/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
    satunya
    -0.91
     cũng
    -0.90
     definición
    -0.86
     also
    -0.84
    깊
    -0.83
    abinieri
    -0.82
    煞
    -0.82
    লা
    -0.82
     ใน
    -0.81
     =>
    -0.80
    POSITIVE LOGITS
     pune
    1.05
     Wishing
    0.86
    헛
    0.82
    ໂ
    0.82
    ถม
    0.82
     comis
    0.82
    getById
    0.81
     vince
    0.80
     bari
    0.80
     semp
    0.80
    Activations Density 0.120%

    No Known Activations