© 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. 25257
    Prev
    Next
    INDEX
    Explanations

    future resolutions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gangen
    -1.03
     inmediata
    -0.99
     inicios
    -0.93
     faktiskt
    -0.93
    циони
    -0.92
    騨
    -0.90
     siquiera
    -0.90
    ianie
    -0.89
    стта
    -0.89
     sterk
    -0.88
    POSITIVE LOGITS
     eventually
    2.39
     soon
    2.14
    eventually
    1.82
    Eventually
    1.76
     Eventually
    1.74
     someday
    1.71
     will
    1.60
     irgendwann
    1.59
    soon
    1.59
     sooner
    1.52
    Activations Density 0.015%

    No Known Activations