© 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. 111474
    Prev
    Next
    INDEX
    Explanations

    differences and improvements

    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
    reviewed
    -1.30
    飧
    -1.27
    selben
    -1.22
    nemu
    -1.22
     ancha
    -1.20
     könnten
    -1.19
     cynical
    -1.19
    selbe
    -1.17
    <bos>
    -1.17
     druk
    -1.15
    POSITIVE LOGITS
     garantis
    1.48
     changes
    1.44
     improvements
    1.41
     pomocí
    1.35
     my
    1.30
     when
    1.28
     increase
    1.28
     egne
    1.27
     difference
    1.27
     piemē
    1.26
    Activations Density 0.035%

    No Known Activations