© 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. 73749
    Prev
    Next
    INDEX
    Explanations

    price ranges

    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
     they
    -1.66
     just
    -1.44
    éricos
    -1.34
     mitte
    -1.33
    仉
    -1.30
     for
    -1.28
     ilustracji
    -1.26
     both
    -1.24
     reise
    -1.20
     himmel
    -1.20
    POSITIVE LOGITS
     and
    1.93
     МВД
    1.28
     этих
    1.28
     této
    1.27
    定価
    1.26
    の前に
    1.26
     piti
    1.25
     
    1.23
     Enables
    1.23
     этой
    1.23
    Activations Density 0.194%

    No Known Activations