© 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. 25564
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    Drei
    -0.93
    propagate
    -0.91
     meuble
    -0.90
    Här
    -0.90
    Premios
    -0.89
    kons
    -0.87
    leville
    -0.85
    Bangladesh
    -0.84
    Tämä
    -0.84
    Zwischen
    -0.84
    POSITIVE LOGITS
     into
    1.05
     analysis
    0.94
     cut
    0.93
     to
    0.92
     lẽ
    0.84
     lack
    0.83
     get
    0.82
    mR
    0.81
    analysis
    0.81
    funko
    0.78
    Activations Density 0.006%

    No Known Activations