© 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. 22-GEMMASCOPE-RES-131K
    7. 130610
    Prev
    Next
    INDEX
    Explanations

    nouns followed by descriptors

    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
     llorar
    -1.14
     ocultar
    -1.01
    媵
    -0.96
     skriv
    -0.95
     outlying
    -0.93
     been
    -0.93
     soweit
    -0.92
     empêcher
    -0.92
    されると
    -0.92
     hvis
    -0.91
    POSITIVE LOGITS
     oneself
    1.27
     for
    1.24
    botas
    1.13
    以及
    1.04
     yourself
    1.02
     versus
    0.98
    НУ
    0.97
     testimonio
    0.96
     involves
    0.95
     сумка
    0.95
    Activations Density 0.193%

    No Known Activations