© 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. 79843
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Ȣ
    -1.15
     constater
    -1.11
     ſur
    -1.07
     COMING
    -1.06
    CHRIS
    -1.06
     promesse
    -1.05
     autonome
    -1.04
     klassi
    -1.03
     اصل
    -1.02
     katk
    -1.02
    POSITIVE LOGITS
     time
    1.63
     at
    1.38
     for
    1.30
     week
    1.24
     with
    1.22
     month
    1.19
     as
    1.16
     October
    1.13
     during
    1.13
     their
    1.13
    Activations Density 0.024%

    No Known Activations