© 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. 3029
    Prev
    Next
    INDEX
    Explanations

    change the course of events

    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
    oció
    -0.88
    angnya
    -0.87
    arik
    -0.84
     recurrir
    -0.84
    ғы
    -0.78
    agian
    -0.75
    Cms
    -0.74
    емый
    -0.74
    kinen
    -0.72
    pytorch
    -0.71
    POSITIVE LOGITS
     changed
    4.09
     changing
    3.80
    改变
    3.73
     change
    3.64
     changes
    3.39
    改變
    3.38
    changed
    3.27
    changing
    3.27
     Changed
    3.22
     mengubah
    3.19
    Activations Density 0.169%

    No Known Activations