© 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. 103129
    Prev
    Next
    INDEX
    Explanations

    running code or functions

    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
    由于
    -0.91
    可以用
    -0.87
    RADIUS
    -0.85
    USED
    -0.82
    gelijke
    -0.82
    nischen
    -0.82
     riding
    -0.81
    illan
    -0.81
    利用
    -0.81
    ensen
    -0.80
    POSITIVE LOGITS
     on
    1.59
     against
    1.57
     errands
    1.55
     tests
    1.54
     experiments
    1.27
     simulations
    1.23
     commands
    1.17
     through
    1.13
    TESTS
    1.10
    tests
    1.09
    Activations Density 0.106%

    No Known Activations