© 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. 16424
    Prev
    Next
    INDEX
    Explanations

    code configuration and credentials

    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
     Semoga
    -1.00
    igrette
    -1.00
    licante
    -1.00
    tonsoft
    -0.97
    ModelAndView
    -0.96
    Nº
    -0.94
     Vorsitzender
    -0.94
    жный
    -0.92
     Fakta
    -0.92
     Ortsteil
    -0.91
    POSITIVE LOGITS
     powie
    0.90
     отвечает
    0.86
    охра
    0.85
     któ
    0.84
     Испа
    0.84
     ЛИ
    0.81
    炆
    0.81
    ֶּ
    0.80
    Примі
    0.78
    cenza
    0.78
    Activations Density 0.009%

    No Known Activations