© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73986
    Prev
    Next
    INDEX
    Explanations

    holding, embracing, arms

    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
    哢
    -2.72
     perdagangan
    -2.69
     短发
    -2.45
    ◆◆
    -2.44
     judul
    -2.36
    ★☆
    -2.33
     guapos
    -2.30
    是怎么
    -2.28
     siano
    -2.27
     redaktion
    -2.25
    POSITIVE LOGITS
    a
    2.70
    1
    2.55
    {
    2.52
    ?
    2.16
    ,
    2.14
     leichte
    2.11
    that
    2.11
     schwere
    2.05
    2.03
    en
    1.97
    Activations Density 0.001%
    No Known Activations