© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11194
    Prev
    Next
    INDEX
    Explanations

    sculpting art, artists, and objects

    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
     Including
    -2.95
     що
    -2.48
     Especially
    -2.45
    s
    -2.42
    This
    -2.41
    2
    -2.34
     Incidentally
    -2.31
    翾
    -2.31
     Atención
    -2.25
     But
    -2.22
    POSITIVE LOGITS
    ↵
    3.06
    ?”
    2.61
     indiquer
    2.38
     consideradas
    2.34
     bijna
    2.33
    臜
    2.27
     самых
    2.23
     gyer
    2.22
     víz
    2.20
    癭
    2.20
    Activations Density 0.003%

    No Known Activations