© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48960
    Prev
    Next
    INDEX
    Explanations

    Matlab software and toolboxes

    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
     Selasa
    -0.81
    ösungen
    -0.72
     uds
    -0.72
     Nikki
    -0.71
    Tablet
    -0.69
    ්‍
    -0.69
     gaat
    -0.69
    ℕ
    -0.68
    ↴
    -0.68
    Sistema
    -0.67
    POSITIVE LOGITS
     toolbox
    2.34
     Toolbox
    1.87
    toolbox
    1.78
    Toolbox
    1.56
     package
    1.20
     library
    1.13
     tools
    1.12
     tool
    1.08
     toolkit
    1.07
     routines
    1.01
    Activations Density 0.050%

    No Known Activations