© 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. 48403
    Prev
    Next
    INDEX
    Explanations

    lists of items or examples

    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
     it
    -1.90
     незавер
    -1.35
     method
    -1.32
     we
    -1.30
     dikem
    -1.25
     bukan
    -1.25
     very
    -1.25
     FBref
    -1.24
     there
    -1.24
     so
    -1.21
    POSITIVE LOGITS
     esimerkiksi
    1.62
     například
    1.52
    などは
    1.45
     tikai
    1.41
     bijvoorbeeld
    1.40
     zwłaszcza
    1.35
     iesp
    1.35
    で
    1.31
    より
    1.30
    OWA
    1.30
    Activations Density 0.092%

    No Known Activations