© 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. 10-GEMMASCOPE-RES-131K
    7. 15707
    Prev
    Next
    INDEX
    Explanations

    shell commands for file and variable manipulation

    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
    Negative Logits
     to
    -2.38
     "
    -2.36
     (
    -1.99
     was
    -1.75
    。"
    -1.61
    </h2>
    -1.59
     
    -1.58
     '
    -1.56
    ↵
    -1.52
     c
    -1.46
    POSITIVE LOGITS
    怱
    1.52
     ТАК
    1.50
    Previously
    1.47
     Grâce
    1.47
     Outros
    1.45
     garcía
    1.45
     становятся
    1.44
     bumi
    1.43
    aimana
    1.43
    Specifically
    1.42
    Activations Density 0.026%

    No Known Activations