© 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. 63821
    Prev
    Next
    INDEX
    Explanations

    action or expression during another

    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
     triliun
    -1.23
    enumerate
    -1.09
     jenis
    -1.05
     capitolo
    -1.02
     menjel
    -1.02
    Clustering
    -1.00
     largas
    -1.00
     general
    -0.98
     kaikk
    -0.98
    を行います
    -0.98
    POSITIVE LOGITS
     while
    1.38
     mentre
    1.25
    while
    1.17
    하면
    1.16
     whilst
    1.09
    
    1.06
     беже
    1.02
     cappella
    1.01
    towards
    0.97
    maining
    0.95
    Activations Density 0.014%

    No Known Activations