© 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. 10-GEMMASCOPE-RES-131K
    7. 43383
    Prev
    Next
    INDEX
    Explanations

    devise, draft, compile, elaborate

    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_10/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
    甗
    -2.16
     debilit
    -2.09
    despite
    -1.95
     remor
    -1.95
    believe
    -1.95
    能在
    -1.93
    鹛
    -1.93
    鹀
    -1.87
     $^{\
    -1.85
     .......
    -1.84
    POSITIVE LOGITS
     This
    2.48
     a
    2.09
     if
    2.06
     list
    2.03
     as
    1.99
    ch
    1.99
    a
    1.99
     what
    1.95
     and
    1.94
    </u>
    1.93
    Activations Density 0.033%

    No Known Activations