© 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. 34-GEMMASCOPE-RES-131K
    4. 34837
    Prev
    Next
    INDEX
    Explanations

    state line

    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
    Comentários
    -0.98
     balení
    -0.94
     informacija
    -0.91
     مناطق
    -0.89
    adorable
    -0.88
     exhibición
    -0.88
     cucharadita
    -0.88
     trzech
    -0.85
    scooter
    -0.85
     малю
    -0.85
    POSITIVE LOGITS
     said
    1.02
     intersection
    0.99
     centerline
    0.97
     line
    0.95
     aforesaid
    0.90
     posts
    0.86
     centre
    0.85
     prolongation
    0.84
     duly
    0.83
     existing
    0.82
    Activations Density 0.013%

    No Known Activations