© 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. 59282
    Prev
    Next
    INDEX
    Explanations

    mediation and intervention

    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
    šní
    -0.87
    JPY
    -0.85
     artig
    -0.83
    vska
    -0.82
     財布
    -0.82
    pted
    -0.80
    CompilerServices
    -0.80
     प्रति
    -0.78
    ază
    -0.77
    Convenient
    -0.77
    POSITIVE LOGITS
     mediation
    3.11
     mediating
    2.88
     mediate
    2.69
     mediator
    2.61
     mediators
    2.48
     mediated
    2.44
     mediates
    2.39
    Medi
    2.36
     Mediation
    2.33
    mediation
    2.25
    Activations Density 0.036%

    No Known Activations