© 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. 10-GEMMASCOPE-RES-131K
    4. 105391
    Prev
    Next
    INDEX
    Explanations

    percentages

    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_10/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
    t
    -1.55
    m
    -1.52
    al
    -1.48
     be
    -1.45
    解读
    -1.45
    也会
    -1.44
    z
    -1.43
    u
    -1.41
    y
    -1.41
     inaprop
    -1.37
    POSITIVE LOGITS
    2
    1.69
     decoradas
    1.66
    dolce
    1.62
    Kelas
    1.62
    besos
    1.55
     cilvē
    1.52
     wszystkie
    1.51
    camisa
    1.48
     pintadas
    1.48
    、“
    1.46
    Activations Density 0.018%

    No Known Activations