© 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. 47908
    Prev
    Next
    INDEX
    Explanations

    question words

    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
     now
    -1.75
     guantes
    -1.27
     Angabe
    -1.24
    ociação
    -1.23
    woordig
    -1.23
     teraz
    -1.20
    だろうか
    -1.18
     />
    -1.18
     capucha
    -1.17
     again
    -1.14
    POSITIVE LOGITS
     they
    1.70
    様々な
    1.34
    全ての
    1.33
     it
    1.32
    あらゆる
    1.24
     Traditionally
    1.23
     Various
    1.18
     ciascuno
    1.16
     Bahkan
    1.16
    多くの
    1.15
    Activations Density 0.145%

    No Known Activations