© 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. 11818
    Prev
    Next
    INDEX
    Explanations

    separators followed by 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
     will
    -1.61
     it
    -1.44
     mosca
    -1.34
     should
    -1.34
     gustar
    -1.30
     cittadino
    -1.29
     sapat
    -1.22
     when
    -1.22
     pneu
    -1.21
    תיים
    -1.20
    POSITIVE LOGITS
     новая
    1.37
     новые
    1.27
     който
    1.27
    owanym
    1.26
     такую
    1.26
     nuevos
    1.26
     работают
    1.25
     červená
    1.24
     nay
    1.23
     вторая
    1.23
    Activations Density 0.091%

    No Known Activations