© 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. 36459
    Prev
    Next
    INDEX
    Explanations

    Amazon, Brain, Imaging, Construction

    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
    reel
    -1.32
    akteur
    -1.17
     levante
    -1.11
     reporta
    -1.11
    natured
    -1.10
    ’:
    -1.09
     this
    -1.09
     avenida
    -1.05
    NSError
    -1.05
    nological
    -1.03
    POSITIVE LOGITS
     Amazon
    1.19
     amazon
    1.19
    Searching
    1.12
    Currently
    1.07
    Amazon
    1.07
    if
    1.05
     również
    1.04
    熟悉的
    1.02
    '
    0.98
    amazon
    0.97
    Activations Density 0.001%

    No Known Activations