© 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. 41111
    Prev
    Next
    INDEX
    Explanations

    contrasting information

    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
     además
    -1.55
     البته
    -1.48
     then
    -1.41
     також
    -1.41
     however
    -1.37
     out
    -1.35
     furthermore
    -1.35
     moreover
    -1.34
     zudem
    -1.34
     again
    -1.29
    POSITIVE LOGITS
     omdat
    1.31
     「
    1.23
    tells
    1.13
    uito
    1.11
    日で
    1.11
     porque
    1.10
    provides
    1.09
     столе
    1.09
    ("
    1.09
    actéristi
    1.09
    Activations Density 0.036%

    No Known Activations