© 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. 119412
    Prev
    Next
    INDEX
    Explanations

    sports and action contexts

    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
     CRO
    -0.79
    צע
    -0.77
    leiding
    -0.75
    颜值
    -0.75
     jovens
    -0.75
    CRA
    -0.73
    ախ
    -0.73
    relax
    -0.73
     ammat
    -0.73
    Isle
    -0.72
    POSITIVE LOGITS
     zone
    1.03
     along
    1.00
     fore
    0.93
     Zone
    0.93
     below
    0.93
     possession
    0.91
     north
    0.88
     puck
    0.84
     Possession
    0.82
     neutral
    0.81
    Activations Density 0.009%

    No Known Activations