© 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. 50193
    Prev
    Next
    INDEX
    Explanations

    function arguments or parameters

    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
    ilerini
    -0.76
    áus
    -0.72
    interno
    -0.72
    れません
    -0.72
     calcareous
    -0.71
    Leslie
    -0.71
    сова
    -0.71
    iziert
    -0.70
    Film
    -0.69
    jQuery
    -0.69
    POSITIVE LOGITS
     présents
    0.82
     according
    0.81
     térm
    0.80
     devuelve
    0.80
     Albion
    0.78
    granted
    0.77
     cães
    0.76
     CoreData
    0.76
     Palma
    0.75
     صفحه
    0.75
    Activations Density 0.001%

    No Known Activations