© 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. 32996
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
    Rendez
    -1.10
    当然是
    -1.08
    trägen
    -1.07
    ℋ
    -1.02
    erir
    -1.02
     reager
    -1.00
    これから
    -1.00
    最初は
    -0.99
     ложка
    -0.98
    Steuer
    -0.98
    POSITIVE LOGITS
     if
    1.23
    if
    1.19
    conut
    0.96
     palha
    0.94
     a
    0.92
     even
    0.91
    iseur
    0.90
    nvarchar
    0.89
    mated
    0.88
    nnnn
    0.87
    Activations Density 0.012%

    No Known Activations