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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68533
    Prev
    Next
    INDEX
    Explanations

    @ or . followed by identifier

    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
    neter
    -1.00
     œufs
    -0.98
    FIM
    -0.98
     BASF
    -0.97
     broek
    -0.96
    ニット
    -0.96
    Swi
    -0.96
    Intérieur
    -0.96
     salonu
    -0.93
     falda
    -0.93
    POSITIVE LOGITS
     even
    0.98
     lahko
    0.97
     this
    0.96
     it
    0.93
    page
    0.89
     on
    0.87
     While
    0.87
     bahkan
    0.84
     verfügen
    0.84
     هذا
    0.82
    Activations Density 0.006%

    No Known Activations