© 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. 32585
    Prev
    Next
    INDEX
    Explanations

    validity or presence checks

    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
     VERY
    -1.66
    あー
    -1.57
    あぁ
    -1.45
     molte
    -1.43
    めっちゃ
    -1.43
     fabulous
    -1.41
     decidedly
    -1.38
     extremely
    -1.38
     soooo
    -1.37
     zwölf
    -1.36
    POSITIVE LOGITS
     in
    1.76
     oddly
    1.56
     after
    1.52
     during
    1.52
     despite
    1.43
     from
    1.36
     new
    1.34
     within
    1.32
     because
    1.30
    しては
    1.30
    Activations Density 0.016%

    No Known Activations