© 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. 45543
    Prev
    Next
    INDEX
    Explanations

    PHP variable names and parameters

    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
     and
    -1.77
     is
    -1.69
     a
    -1.63
     has
    -1.41
     seguintes
    -1.38
     in
    -1.28
     awkward
    -1.23
     have
    -1.16
     extremely
    -1.16
     I
    -1.13
    POSITIVE LOGITS
    ERVIEW
    1.50
    弒
    1.41
    hasilkan
    1.37
     thuật
    1.34
    マイズ
    1.33
     estekak
    1.31
    itaria
    1.31
     męski
    1.29
    izate
    1.29
     anledning
    1.28
    Activations Density 0.011%

    No Known Activations