© 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. 34-GEMMASCOPE-RES-131K
    7. 62447
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Consequently
    -1.62
    -1.47
     délais
    -1.44
     rafraî
    -1.42
     apprehen
    -1.36
     précé
    -1.36
    Nowadays
    -1.36
     élabor
    -1.35
    🎱
    -1.34
    Successfully
    -1.32
    POSITIVE LOGITS
     again
    1.77
     also
    1.35
    而后
    1.34
     additionally
    1.30
     ebenso
    1.22
     now
    1.20
     even
    1.19
     цей
    1.12
     needed
    1.11
     possibly
    1.11
    Activations Density 0.294%

    No Known Activations