© 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. 123530
    Prev
    Next
    INDEX
    Explanations

    select/Select element

    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
     oogen
    -1.95
     to
    -1.72
     proteine
    -1.52
     geforce
    -1.51
     doos
    -1.45
    ペーパー
    -1.44
    踽
    -1.43
     bringe
    -1.41
     heu
    -1.39
     $_=
    -1.34
    POSITIVE LOGITS
     this
    1.66
     with
    1.63
     Verkäufer
    1.63
     Eigentü
    1.52
     bowiem
    1.50
     више
    1.46
     other
    1.45
    他の
    1.44
     још
    1.44
     any
    1.41
    Activations Density 0.003%

    No Known Activations