© 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. 68623
    Prev
    Next
    INDEX
    Explanations

    home and domestic spaces

    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
    asiswa
    -1.26
    DBNull
    -1.18
     konfigura
    -1.17
     JOHN
    -1.17
     jaka
    -1.16
    abinieri
    -1.14
    ᚔ
    -1.11
    ឵
    -1.09
    änderungen
    -1.09
     tbody
    -1.09
    POSITIVE LOGITS
     where
    1.35
     home
    1.33
        
    1.30
     hemma
    1.24
     приготовить
    1.18
    これは
    1.11
           
    1.10
     is
    1.09
       
    1.07
     or
    1.07
    Activations Density 0.029%

    No Known Activations