© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47938
    Prev
    Next
    INDEX
    Explanations

    assembly attributes

    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_34/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
    resizeMode
    -0.83
    thoven
    -0.65
    ærer
    -0.64
     Widget
    -0.64
    bender
    -0.63
     Evaluación
    -0.62
    šil
    -0.62
     ند
    -0.61
     helicópter
    -0.61
    اري
    -0.61
    POSITIVE LOGITS
    ∅
    0.77
    솜
    0.72
     blah
    0.71
    mbolic
    0.71
    bonucleic
    0.71
    Blanc
    0.70
     nostrils
    0.66
    ginous
    0.65
    retung
    0.65
    chitz
    0.64
    Activations Density 0.061%

    No Known Activations