© 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. 112766
    Prev
    Next
    INDEX
    Explanations

    method/function calls

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

    the `viewDidLoad` method declaration in iOS/macOS code.

    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
     mereka
    -2.28
    mpagne
    -1.95
     setiap
    -1.94
     vaak
    -1.83
    梛
    -1.81
     nicknamed
    -1.78
    嵎
    -1.75
     vooral
    -1.74
    aarrggbb
    -1.73
     kemudian
    -1.73
    POSITIVE LOGITS
    .
    2.91
    3
    1.88
    𓆜
    1.77
     старый
    1.75
    </sup>
    1.71
    赜
    1.70
    6
    1.68
    ,
    1.64
     betrug
    1.63
     examinar
    1.63
    Activations Density 0.002%

    No Known Activations