© 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. 10-GEMMASCOPE-RES-131K
    7. 123997
    Prev
    Next
    INDEX
    Explanations

    programming constructs and libraries

    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_10/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
     отличается
    -1.41
    {\$
    -1.41
     avancer
    -1.40
    话音
    -1.38
    гают
    -1.37
     exercices
    -1.36
    どうやら
    -1.35
     glaubte
    -1.34
    一旁的
    -1.34
    喁
    -1.34
    POSITIVE LOGITS
     that
    1.38
     which
    1.38
    manın
    1.34
     such
    1.34
     on
    1.34
    <bos>
    1.33
    RSpec
    1.33
     needed
    1.32
     That
    1.29
     Поэтому
    1.29
    Activations Density 0.036%

    No Known Activations