© 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. 56800
    Prev
    Next
    INDEX
    Explanations

    ending states or periods

    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
     météo
    -0.93
     otomatig
    -0.90
    Success
    -0.88
    Again
    -0.88
     أثناء
    -0.87
    接下来的
    -0.85
    again
    -0.85
     wieder
    -0.85
     अनुसार
    -0.84
    Still
    -0.83
    POSITIVE LOGITS
     era
    1.46
     reign
    1.30
     chapter
    1.25
     saga
    1.20
     hostilities
    1.16
     cycle
    1.13
     dependence
    1.09
     ended
    1.09
     streak
    1.07
     period
    1.05
    Activations Density 0.037%

    No Known Activations