© 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. 102536
    Prev
    Next
    INDEX
    Explanations

    UI elements and controls

    np_acts-logits-general · gemini-2.5-flash-lite

    UI component names and programming identifiers in iOS/Swift code, particularly labels, views, buttons, and controls.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     of
    -2.03
    to
    -1.81
     как
    -1.75
     tanpa
    -1.65
    //
    -1.60
    code
    -1.59
    ena
    -1.57
    info
    -1.52
    ↵
    -1.52
    by
    -1.48
    POSITIVE LOGITS
    </h3>
    1.51
    甞
    1.45
     zvíř
    1.45
     plenamente
    1.43
    jaqueta
    1.40
     aktiviteter
    1.38
     fous
    1.35
     petróleo
    1.35
    {
    1.35
    Selamat
    1.34
    Activations Density 0.039%

    No Known Activations