© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35632
    Prev
    Next
    INDEX
    Explanations

    state or process descriptions

    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
    -1.34
     They
    -1.03
     are
    -1.03
    들이
    -1.03
     они
    -1.02
     которые
    -1.02
     mobilen
    -1.01
     έχουν
    -1.00
     装置
    -0.98
     Agustus
    -0.97
    POSITIVE LOGITS
     done
    1.41
     itself
    1.27
     occurs
    1.18
     happening
    1.16
     performed
    1.09
     acompañada
    1.07
     occurring
    1.07
     odby
    1.05
    着一
    1.04
    occurs
    1.04
    Activations Density 0.277%

    No Known Activations