© 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. 10-GEMMASCOPE-RES-131K
    7. 128853
    Prev
    Next
    INDEX
    Explanations

    after durations of time

    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_10/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
     thing
    -1.59
     gegebenen
    -1.48
     without
    -1.44
     treasured
    -1.43
     what
    -1.41
     three
    -1.41
     before
    -1.41
     went
    -1.40
     small
    -1.39
     if
    -1.38
    POSITIVE LOGITS
     THESE
    1.51
    >
    1.47
     apenas
    1.45
     seulement
    1.45
    其他
    1.44
    
    1.41
    для
    1.39
    ⎔
    1.38
    ğan
    1.35
     других
    1.34
    Activations Density 0.031%

    No Known Activations