© 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. 127983
    Prev
    Next
    INDEX
    Explanations

    for example

    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
     multicolore
    -1.02
    within
    -0.98
     illustrationer
    -0.97
     serons
    -0.94
     rurale
    -0.93
    ika
    -0.93
     construite
    -0.91
    後で
    -0.91
    without
    -0.91
     придется
    -0.90
    POSITIVE LOGITS
    坊
    1.00
     joten
    0.98
     solution
    0.93
    şap
    0.90
     two
    0.89
    слова
    0.89
     system
    0.89
    сну
    0.88
    upuk
    0.88
     przechowy
    0.88
    Activations Density 0.219%

    No Known Activations