© 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. 32810
    Prev
    Next
    INDEX
    Explanations

    testing outcomes

    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
     also
    -1.38
     berikan
    -1.30
    represents
    -1.18
     These
    -1.16
    aussi
    -1.11
     these
    -1.09
     inginkan
    -1.09
    ⸻
    -1.08
    continues
    -1.07
     eksklu
    -1.05
    POSITIVE LOGITS
     correct
    1.11
    怎么说
    1.02
    a
    1.01
    起码
    0.97
    稅
    0.96
     nanop
    0.96
    umbus
    0.96
    れました
    0.96
     sesame
    0.94
    ∂
    0.94
    Activations Density 0.005%

    No Known Activations