© 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. 23529
    Prev
    Next
    INDEX
    Explanations

    statistical learning and decision analysis

    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
     Adi
    -0.77
    colorbar
    -0.76
     infir
    -0.73
     $_{\
    -0.73
     prison
    -0.72
     কর
    -0.71
     isoto
    -0.71
    onCreate
    -0.71
     $_{
    -0.71
    KEA
    -0.70
    POSITIVE LOGITS
     Lehmann
    0.96
     decision
    0.91
     Decision
    0.87
     loss
    0.83
     family
    0.82
     losses
    0.81
    decision
    0.80
    Семья
    0.80
    决策
    0.80
    produto
    0.79
    Activations Density 0.062%

    No Known Activations