© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11180
    Prev
    Next
    INDEX
    Explanations

    code comments and directives

    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_22/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
    -0.98
    ored
    -0.86
     shorts
    -0.78
     бру
    -0.78
    があって
    -0.77
     dzięki
    -0.77
     anti
    -0.75
     Bor
    -0.75
    爆发
    -0.75
     a
    -0.75
    POSITIVE LOGITS
    XDD
    0.91
    Nevertheless
    0.90
     schia
    0.88
     fasi
    0.86
     витами
    0.86
     pastillas
    0.86
    endung
    0.86
     ""),
    0.85
    ainan
    0.85
     Revista
    0.85
    Activations Density 0.005%

    No Known Activations