© 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. 13433
    Prev
    Next
    INDEX
    Explanations

    I really

    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
     this
    -1.33
     it
    -1.17
     Lokales
    -1.16
    arschu
    -1.12
     alarme
    -1.10
    ˝
    -1.09
     akces
    -1.07
     reseñas
    -1.06
    sikker
    -1.05
     pido
    -1.05
    POSITIVE LOGITS
    なども
    1.50
     favorites
    1.17
     among
    1.13
    どれも
    1.13
     of
    1.13
     most
    1.11
    들을
    1.11
     those
    1.09
     really
    1.07
    分别是
    1.07
    Activations Density 0.025%

    No Known Activations