© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75391
    Prev
    Next
    INDEX
    Explanations

    compound words and suffixes

    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
     koje
    -1.48
     violación
    -1.44
    ﮦ
    -1.43
     viviendas
    -1.38
     informaron
    -1.36
     gjort
    -1.35
     those
    -1.34
     będzie
    -1.34
     veía
    -1.33
     kurulan
    -1.33
    POSITIVE LOGITS
    hline
    1.75
     of
    1.55
     or
    1.51
     elas
    1.49
    </h2>
    1.48
    \}$.
    1.47
    }}$.
    1.36
     entire
    1.36
    <h3>
    1.35
    $}
    1.34
    Activations Density 0.070%

    No Known Activations