© 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. 47327
    Prev
    Next
    INDEX
    Explanations

    saving and improvement

    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
    Ĝ
    -0.82
    fg
    -0.78
    instorm
    -0.78
     мя
    -0.77
     turmoil
    -0.75
    だれ
    -0.74
    続いて
    -0.73
     لغ
    -0.72
    rdom
    -0.71
    enumi
    -0.67
    POSITIVE LOGITS
     improvement
    1.25
     early
    1.13
    improvement
    1.13
     patience
    1.13
     improvements
    1.08
     improve
    1.07
     Improvement
    1.05
    Improvement
    1.05
     saving
    1.00
    saver
    0.98
    Activations Density 0.005%

    No Known Activations