© 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. 34987
    Prev
    Next
    INDEX
    Explanations

    match play golf

    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
     coordinators
    -0.79
     coordination
    -0.75
     mone
    -0.74
    ﷲ
    -0.74
     エコ
    -0.73
     asociados
    -0.70
     capa
    -0.69
     seen
    -0.69
    オク
    -0.69
     stri
    -0.69
    POSITIVE LOGITS
     dorm
    1.13
     square
    1.02
    Matches
    0.97
    dorm
    0.93
    Match
    0.93
    Squared
    0.90
    square
    0.86
     Dorm
    0.84
     match
    0.84
     matches
    0.83
    Activations Density 0.013%

    No Known Activations