© 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. 2705
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     furthering
    -1.47
     unrelenting
    -1.45
     enticing
    -1.42
     meticulous
    -1.39
     continual
    -1.39
     after
    -1.37
     placing
    -1.37
     frantic
    -1.35
     dazzling
    -1.35
     five
    -1.35
    POSITIVE LOGITS
     amd
    1.62
     السياس
    1.55
     lauded
    1.39
     boister
    1.38
     magnific
    1.38
     unn
    1.34
     pivotal
    1.34
     ludicrous
    1.33
     gigantic
    1.30
     revamped
    1.29
    Activations Density 0.016%

    No Known Activations