© 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. 22-GEMMASCOPE-RES-131K
    7. 11174
    Prev
    Next
    INDEX
    Explanations

    website links and navigation

    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
     mengatakan
    -1.08
     siku
    -1.08
     deinen
    -1.08
     PTA
    -1.05
     żeby
    -1.04
     gebeten
    -1.00
     może
    -1.00
    <b>
    -0.99
    anmoins
    -0.96
    <h3>
    -0.96
    POSITIVE LOGITS
     www
    1.90
    www
    1.66
     on
    1.56
     at
    1.55
     online
    1.55
    wwww
    1.30
     http
    1.28
    Www
    1.28
     website
    1.27
    givings
    1.22
    Activations Density 0.046%

    No Known Activations