© 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. 11168
    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
    兩
    -1.47
    .”
    -1.27
     *
    -1.25
     x
    -1.24
    !”
    -1.22
     D
    -1.20
    &#
    -1.19
    _{
    -1.19
     C
    -1.18
     ?
    -1.17
    POSITIVE LOGITS
     mantém
    1.45
     actualité
    1.38
    Untuk
    1.38
    ਖ਼
    1.36
     简约
    1.29
     имел
    1.25
    Taf
    1.25
     huile
    1.24
    
    1.24
    Suka
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.