© 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. 39147
    Prev
    Next
    INDEX
    Explanations

    variable or code element

    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
     a
    -1.82
     said
    -1.60
    n
    -1.58
    ?"
    -1.51
    ış
    -1.48
     is
    -1.46
    </h2>
    -1.41
     ключе
    -1.41
    different
    -1.41
    ").
    -1.41
    POSITIVE LOGITS
    これも
    1.39
     most
    1.38
     with
    1.34
    最近は
    1.34
    香りが
    1.33
     where
    1.33
     which
    1.33
     giù
    1.31
    譙
    1.30
     and
    1.27
    Activations Density 0.047%

    No Known Activations