© 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. 84154
    Prev
    Next
    INDEX
    Explanations

    email addresses or copyrights

    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
    hå
    -0.96
     lakhs
    -0.91
     deterior
    -0.91
    landaise
    -0.91
    アート
    -0.90
     lacrosse
    -0.90
     Selv
    -0.88
    Hvad
    -0.87
     вашего
    -0.86
    érienne
    -0.86
    POSITIVE LOGITS
    github
    1.02
     both
    0.88
     these
    0.86
     Systems
    0.86
     systems
    0.82
     non
    0.80
     almost
    0.80
    GitHub
    0.80
     those
    0.79
     GitHub
    0.78
    Activations Density 0.136%

    No Known Activations