© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25056
    Prev
    Next
    INDEX
    Explanations

    dates followed by commas

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ómo
    -1.09
     toalla
    -1.02
    的最大
    -1.00
     عزیزم
    -0.98
    はい
    -0.96
     années
    -0.95
     anillos
    -0.95
     cordones
    -0.94
     aarde
    -0.94
    ">(</
    -0.93
    POSITIVE LOGITS
     otros
    0.98
    疝
    0.98
    onError
    0.98
    other
    0.96
     to
    0.94
    Tetrach
    0.94
    einander
    0.93
    ↵↵
    0.91
    onStart
    0.91
     work
    0.91
    Activations Density 0.030%

    No Known Activations