© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93263
    Prev
    Next
    INDEX
    Explanations

    numbers and code elements

    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
     strange
    -1.00
     so
    -0.97
     by
    -0.96
     strangely
    -0.92
     weird
    -0.89
     What
    -0.88
     does
    -0.87
    chaik
    -0.86
     never
    -0.85
    Obviously
    -0.85
    POSITIVE LOGITS
    Permalink
    0.98
    ~"
    0.94
    权利
    0.92
    TagHelpers
    0.89
    ⌗
    0.89
     signif
    0.87
     Alamy
    0.87
     insinu
    0.87
    !“
    0.86
    矧
    0.85
    Activations Density 0.002%

    No Known Activations