© 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. 104775
    Prev
    Next
    INDEX
    Explanations

    will often followed by a verb

    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
    Ⓡ
    -1.35
     uska
    -1.34
     แล้ว
    -1.32
    ētu
    -1.30
     lepro
    -1.30
    IVAN
    -1.29
    udnio
    -1.24
    ACIONES
    -1.24
    MAI
    -1.23
    ïc
    -1.22
    POSITIVE LOGITS
    However
    1.48
     gegenwär
    1.48
     erlä
    1.36
     Regionen
    1.34
     vorhandenen
    1.34
     erläut
    1.32
     thing
    1.29
    but
    1.28
     and
    1.27
    But
    1.27
    Activations Density 0.096%

    No Known Activations