© 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. 58335
    Prev
    Next
    INDEX
    Explanations

    indexPath identifier

    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
     و
    -1.63
    และ
    -1.53
    を与
    -1.40
    mlink
    -1.35
     และ
    -1.32
    撂
    -1.27
     whimsical
    -1.27
    arraycopy
    -1.25
    yarnpkg
    -1.25
     remarkably
    -1.25
    POSITIVE LOGITS
     that
    2.48
     will
    1.82
     hornear
    1.80
     who
    1.71
     whose
    1.69
     or
    1.63
     want
    1.55
     which
    1.41
     hogy
    1.35
    已經
    1.34
    Activations Density 0.011%

    No Known Activations