© 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. 10-GEMMASCOPE-RES-131K
    7. 70484
    Prev
    Next
    INDEX
    Explanations

    shal shall shallots shenanigans alertDialog shallow Matthias Axios Sush

    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
     spezielle
    -2.67
     has
    -2.56
     offizielle
    -2.52
     This
    -2.48
     get
    -2.44
     letzte
    -2.41
     sogenannte
    -2.39
     selben
    -2.38
     genaue
    -2.36
     welchem
    -2.34
    POSITIVE LOGITS
    穑
    2.42
    箧
    2.34
     ſtate
    2.33
     drit
    2.22
    要在
    2.22
    AND
    2.20
    要说
    2.19
     lilla
    2.19
    埏
    2.17
    could
    2.13
    Activations Density 0.001%

    No Known Activations