© 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. 34658
    Prev
    Next
    INDEX
    Explanations

    new BorderLayout, INFO:, #!/usr, TITLE, Supported employment, To complete, As a

    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
     sillä
    -0.75
     Functions
    -0.73
     Bericht
    -0.73
    reicher
    -0.72
     Bewertung
    -0.72
    Weekend
    -0.72
    奈川
    -0.72
     χει
    -0.71
     ilç
    -0.70
     Function
    -0.70
    POSITIVE LOGITS
     initComponents
    0.87
     javax
    0.84
    GroupLayout
    0.84
     Manas
    0.82
     Gior
    0.81
     сро
    0.80
     PLO
    0.80
    overrightarrow
    0.76
     GAB
    0.74
     кре
    0.73
    Activations Density 0.000%

    No Known Activations