© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2790
    Prev
    Next
    INDEX
    Explanations

    CSS margin properties

    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
     such
    -1.00
     während
    -0.82
    setLayoutManager
    -0.77
    “……”
    -0.77
     Мексика
    -0.75
     EAST
    -0.75
    mixed
    -0.74
    সূ
    -0.74
    scrollLeft
    -0.73
    اصيل
    -0.73
    POSITIVE LOGITS
     marginTop
    2.58
    marginTop
    2.45
     margin
    1.93
     mt
    1.86
    margin
    1.78
    mt
    1.58
     Margin
    1.47
     marginBottom
    1.44
    Margin
    1.42
     margins
    1.41
    Activations Density 0.025%

    No Known Activations