© 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. 70887
    Prev
    Next
    INDEX
    Explanations

    react syntax and testing imports

    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
     our
    -1.37
    astră
    -1.10
     compared
    -1.05
    iliares
    -1.04
    DIRECTORY
    -1.03
     parameters
    -1.01
     termination
    -1.00
     will
    -1.00
     conditions
    -0.99
     from
    -0.96
    POSITIVE LOGITS
    但却
    1.23
    但这
    1.12
    诠
    1.08
     laajenta
    1.02
    难以
    1.00
    MBC
    0.97
    不一样的
    0.97
    街头
    0.97
     fumée
    0.97
     Allí
    0.97
    Activations Density 0.001%

    No Known Activations