© 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. 45701
    Prev
    Next
    INDEX
    Explanations

    third smallest

    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
     également
    -1.82
    也
    -1.55
     jedynie
    -1.53
     również
    -1.52
     também
    -1.43
    只是
    -1.41
    somewhat
    -1.41
    où
    -1.40
     où
    -1.36
     enorm
    -1.35
    POSITIVE LOGITS
     then
    2.25
     more
    1.82
     in
    1.72
     most
    1.71
     After
    1.66
     not
    1.66
     this
    1.59
     thinks
    1.59
    𖥧
    1.51
     people
    1.48
    Activations Density 0.178%

    No Known Activations