© 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. 127900
    Prev
    Next
    INDEX
    Explanations

    quantities and engagement

    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
    Negative Logits
     only
    -1.01
     ostensibly
    -0.99
    outWeight
    -0.94
     for
    -0.93
    Recently
    -0.92
     should
    -0.91
     can
    -0.90
     Recently
    -0.90
     Anderson
    -0.89
     After
    -0.88
    POSITIVE LOGITS
     thousands
    1.29
    hundreds
    1.11
    thousands
    1.11
     online
    1.05
     popular
    1.05
    ひた
    0.99
     بیش
    0.97
     responded
    0.96
    Response
    0.94
    了出去
    0.94
    Activations Density 0.104%

    No Known Activations