© 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. 116671
    Prev
    Next
    INDEX
    Explanations

    legal burden or onus

    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
    ideration
    -0.79
     "),
    -0.79
    `),
    -0.78
    TypeDef
    -0.77
    *********/
    -0.76
    »),
    -0.75
     Michaelis
    -0.74
    enties
    -0.73
     ráp
    -0.72
     perfil
    -0.72
    POSITIVE LOGITS
     burden
    4.41
    burden
    3.61
     Burden
    3.30
     burdens
    2.67
     onus
    2.56
     burdened
    2.06
    Bur
    1.91
     BUR
    1.54
    onus
    1.43
    负担
    1.43
    Activations Density 0.016%

    No Known Activations