© 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. 20399
    Prev
    Next
    INDEX
    Explanations

    academic references

    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
    two
    -1.81
     ($("#
    -1.65
    They
    -1.61
     two
    -1.59
    First
    -1.52
     your
    -1.52
    Two
    -1.51
    および
    -1.45
    three
    -1.45
    their
    -1.43
    POSITIVE LOGITS
    nunca
    1.42
    そこに
    1.40
    rinol
    1.35
    わけです
    1.34
     dacă
    1.34
     in
    1.34
     provavelmente
    1.33
    muito
    1.33
     özellikle
    1.33
    también
    1.32
    Activations Density 0.002%

    No Known Activations