© 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. 36061
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
     while
    -0.88
     by
    -0.85
     here
    -0.83
    となりました
    -0.79
    黴
    -0.77
     положении
    -0.77
    na
    -0.76
     eh
    -0.75
     ed
    -0.75
     Gottlieb
    -0.75
    POSITIVE LOGITS
     dismin
    0.99
    ཉ
    0.96
    droje
    0.95
    jarse
    0.94
    pintura
    0.94
    thig
    0.93
     pét
    0.93
     origini
    0.92
    TagHelpers
    0.91
     raport
    0.91
    Activations Density 0.006%

    No Known Activations