© 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. 10-GEMMASCOPE-RES-131K
    7. 21340
    Prev
    Next
    INDEX
    Explanations

    Political leadership and government roles

    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
    嵓
    -1.66
     situazioni
    -1.64
    厹
    -1.55
     épu
    -1.48
    </h3>
    -1.39
     レモン
    -1.38
     spezif
    -1.37
     nuove
    -1.35
     alcuni
    -1.35
     các
    -1.32
    POSITIVE LOGITS
     at
    2.27
     after
    1.59
     with
    1.48
     an
    1.45
     or
    1.44
     without
    1.41
    ,
    1.34
     before
    1.28
     getting
    1.26
     despite
    1.22
    Activations Density 0.130%

    No Known Activations