© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129688
    Prev
    Next
    INDEX
    Explanations

    coordinates and dimensions

    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
    mathrm
    -1.31
     such
    -1.15
     poiché
    -1.02
    uccino
    -0.98
     ответить
    -0.97
    other
    -0.97
    在乎
    -0.96
    这么
    -0.95
    ization
    -0.93
     inklusive
    -0.93
    POSITIVE LOGITS
    utilité
    1.00
    éclairage
    0.94
    汎
    0.92
    uestran
    0.89
     директор
    0.89
    Enllaços
    0.88
     convient
    0.88
    भग
    0.88
    Correspond
    0.85
    寝る
    0.85
    Activations Density 0.006%

    No Known Activations