© 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. 56967
    Prev
    Next
    INDEX
    Explanations

    purposeful actions after "to"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    前は
    -1.14
    分けて
    -1.14
    tioners
    -1.09
    urée
    -1.09
     telefónica
    -1.04
     automática
    -0.99
    esseract
    -0.98
     själ
    -0.96
     includes
    -0.95
    岀
    -0.95
    POSITIVE LOGITS
     möglichst
    1.62
     provide
    1.57
     enable
    1.52
    ให้
    1.33
     ensure
    1.30
    Provide
    1.29
    ทำให้
    1.25
     allow
    1.23
     eventually
    1.20
    warz
    1.19
    Activations Density 0.115%

    No Known Activations