© 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. 34-GEMMASCOPE-RES-131K
    7. 56082
    Prev
    Next
    INDEX
    Explanations

    numbers and academic citations

    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_34/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
     gick
    -0.79
    菲
    -0.75
     dėl
    -0.73
    Typography
    -0.71
     autocomplete
    -0.71
     दें
    -0.70
     Pep
    -0.68
    澆
    -0.68
    ходя
    -0.68
     dulce
    -0.67
    POSITIVE LOGITS
     Abschnitt
    0.86
     modernos
    0.79
    を切り
    0.77
    праж
    0.77
    CUT
    0.74
    गत
    0.73
    ᛫
    0.72
    をか
    0.71
    riel
    0.71
    william
    0.71
    Activations Density 0.016%

    No Known Activations