© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39715
    Prev
    Next
    INDEX
    Explanations

    code blocks with special characters

    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_22/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
     rafraî
    -1.20
     réinitial
    -1.18
     três
    -1.14
     polaire
    -1.09
     három
    -1.05
     discuter
    -1.05
     både
    -1.03
     démo
    -1.02
     éte
    -1.00
     dét
    -1.00
    POSITIVE LOGITS
     all
    1.41
     it
    1.27
     usually
    1.20
     with
    1.20
     in
    1.18
     after
    1.15
     new
    1.14
     prevents
    1.13
     there
    1.11
     only
    1.11
    Activations Density 0.001%

    No Known Activations