© 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. 22-GEMMASCOPE-RES-131K
    7. 66697
    Prev
    Next
    INDEX
    Explanations

    Similar Content, Price, Questions

    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_22/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
     anadolu
    -1.01
     lát
    -0.91
    ᾽
    -0.91
     kasa
    -0.90
    不好意思
    -0.90
     its
    -0.90
     susun
    -0.89
    medskip
    -0.87
     Railways
    -0.86
     déli
    -0.86
    POSITIVE LOGITS
    сумка
    1.02
    ◞
    0.98
    這裡
    0.96
    vbox
    0.96
    govine
    0.96
    romptu
    0.95
    Może
    0.94
    Angebot
    0.94
    spania
    0.93
    lawayo
    0.93
    Activations Density 0.000%

    No Known Activations