© 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. 34-GEMMASCOPE-RES-131K
    7. 53890
    Prev
    Next
    INDEX
    Explanations

    code blocks or comments

    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_34/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
     Richard
    -0.89
     avoiding
    -0.88
     made
    -0.87
     constant
    -0.85
     persistent
    -0.82
     Andrew
    -0.82
     its
    -0.82
    ētu
    -0.80
     make
    -0.80
     not
    -0.79
    POSITIVE LOGITS
    篑
    0.94
     verificación
    0.91
    шивания
    0.88
    ᛚ
    0.88
     HOS
    0.87
    züglich
    0.87
    Zona
    0.87
    
    0.85
     ESM
    0.85
     localización
    0.85
    Activations Density 0.001%

    No Known Activations