© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91590
    Prev
    Next
    INDEX
    Explanations

    slab or floor

    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
     tuyến
    -0.72
     空間
    -0.69
    debit
    -0.67
    cence
    -0.66
    優雅
    -0.66
    orice
    -0.66
    ansing
    -0.65
     Stanton
    -0.65
    ඛ
    -0.64
    blick
    -0.64
    POSITIVE LOGITS
     slab
    2.86
     slabs
    2.33
     Slab
    2.30
    slab
    2.17
    Slab
    2.11
     floor
    1.70
     Sla
    1.64
     floors
    1.49
    Sla
    1.47
    floor
    1.31
    Activations Density 0.034%

    No Known Activations