© 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. 127643
    Prev
    Next
    INDEX
    Explanations

    system detail/outcome

    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
    は
    -1.34
    が
    -1.27
    8
    -1.21
    is
    -1.17
    s
    -1.14
    5
    -1.11
     "
    -1.10
    を
    -1.09
    には
    -1.09
    も
    -1.08
    POSITIVE LOGITS
     and
    1.38
    empleado
    1.34
    ごとの
    1.27
    encre
    1.27
    必要がある
    1.26
    blusa
    1.22
    に入れる
    1.21
     AÑO
    1.20
     DÍA
    1.19
    の方も
    1.18
    Activations Density 0.081%

    No Known Activations