© 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. 22-GEMMASCOPE-RES-131K
    4. 84340
    Prev
    Next
    INDEX
    Explanations

    sports matches and legal cases

    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_22/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
    や
    -1.08
    Something
    -1.05
    Perhaps
    -0.96
     Cualquier
    -0.95
     sadar
    -0.95
    Which
    -0.94
    If
    -0.94
     if
    -0.93
     TÉCNICA
    -0.93
    そして
    -0.92
    POSITIVE LOGITS
    orra
    1.13
     Wählen
    1.05
     utan
    0.95
     അ
    0.91
    ährlich
    0.91
     Consistency
    0.90
     Lesen
    0.89
    റി
    0.88
     tied
    0.88
     aqu
    0.87
    Activations Density 0.004%

    No Known Activations