© 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. 66695
    Prev
    Next
    INDEX
    Explanations

    technical terms and mixed languages

    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
    unno
    -1.02
    viembre
    -1.01
    britanni
    -1.01
     Ilustra
    -1.01
     FirebaseAuth
    -0.97
    让他们
    -0.97
    حيح
    -0.96
     asma
    -0.96
     Kristus
    -0.96
     neta
    -0.96
    POSITIVE LOGITS
     existing
    1.15
     fellow
    1.04
     sorpresas
    1.00
     unsere
    0.98
    提出的
    0.97
     + 
    0.96
     opposing
    0.95
     strong
    0.94
     nossa
    0.92
     dispuesto
    0.91
    Activations Density 0.001%

    No Known Activations