© 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. 100154
    Prev
    Next
    INDEX
    Explanations

    programming properties and identifiers

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

    words related to technical programming concepts, particularly when describing data structures, functions, objects, and their properties or parameters.

    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
     or
    -2.34
     if
    -2.08
     by
    -1.85
     even
    -1.72
     more
    -1.48
     increased
    -1.45
     only
    -1.39
     less
    -1.38
     in
    -1.37
     increase
    -1.37
    POSITIVE LOGITS
    %;
    1.71
    -
    1.70
     ();
    1.70
     rése
    1.58
    ILERS
    1.55
    Bjs
    1.53
     ;
    1.50
     rechange
    1.49
     tejto
    1.49
    sudadera
    1.49
    Activations Density 0.340%

    No Known Activations