© 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. 16615
    Prev
    Next
    INDEX
    Explanations

    true or success

    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
     or
    -1.47
     which
    -1.37
     that
    -1.33
     will
    -1.30
     this
    -1.23
     should
    -1.12
     cannot
    -1.06
     out
    -1.05
     whose
    -1.02
     has
    -1.02
    POSITIVE LOGITS
    despite
    1.10
    albeit
    1.09
     bizarre
    1.07
    美味しく
    1.05
     magnific
    1.05
    ​​​
    1.02
    壁纸
    1.01
     astonishing
    1.00
     absurd
    0.99
     deline
    0.99
    Activations Density 0.021%

    No Known Activations