© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72566
    Prev
    Next
    INDEX
    Explanations

    dates and entries

    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
     они
    -1.00
     by
    -0.98
     dabar
    -0.98
     mereka
    -0.96
     regardless
    -0.96
     beträ
    -0.94
     irrespective
    -0.93
     funcion
    -0.93
    enity
    -0.91
     Numerous
    -0.91
    POSITIVE LOGITS
     grafik
    1.20
     teks
    1.05
     plik
    1.00
     karton
    0.98
     izo
    0.95
     eksp
    0.95
     his
    0.94
     rhestr
    0.93
     napisał
    0.93
     Bé
    0.93
    Activations Density 0.001%

    No Known Activations