© 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. 81104
    Prev
    Next
    INDEX
    Explanations

    player names and positions

    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
     turist
    -0.87
     indien
    -0.87
    చ్
    -0.86
     tertutup
    -0.86
     uniques
    -0.84
     absl
    -0.82
    хни
    -0.81
     simbol
    -0.80
     organik
    -0.80
     Elm
    -0.79
    POSITIVE LOGITS
     safety
    0.77
     vulnerable
    0.72
    对
    0.71
     tackled
    0.70
     Snacks
    0.70
    rimp
    0.70
     STI
    0.69
    Breast
    0.68
     вид
    0.68
     પર
    0.68
    Activations Density 0.041%

    No Known Activations