© 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. 80691
    Prev
    Next
    INDEX
    Explanations

    machine computer microcomputer

    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
    Plumbing
    -0.81
     wish
    -0.81
    бла
    -0.77
    Wish
    -0.76
     wished
    -0.76
    ıldız
    -0.74
    Chau
    -0.74
     wishlist
    -0.73
    屬
    -0.71
    扁
    -0.71
    POSITIVE LOGITS
     Alta
    1.06
     Wo
    0.92
     Intel
    0.86
     hobby
    0.83
     Keyboard
    0.82
     Couples
    0.82
     Paulo
    0.81
    ulman
    0.81
    Alta
    0.81
     Washington
    0.79
    Activations Density 0.020%

    No Known Activations