© 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. 34-GEMMASCOPE-RES-131K
    4. 118304
    Prev
    Next
    INDEX
    Explanations

    code imports and modules

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on the individual identifier segments (like “domain,” “utils,” “exception,” “model,” etc.) in Java package and import paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ||
    
    -1.16
    でしたね
    -1.06
    定価
    -1.06
    jmuje
    -1.05
     ・
    -1.03
     segíts
    -1.01
    にあります
    -1.00
    おわりに
    -1.00
     джин
    -0.99
    روید
    -0.98
    POSITIVE LOGITS
    もある
    1.31
    なので
    1.26
    では
    1.23
    が
    1.17
    maan
    1.10
     intertw
    1.10
    met
    1.08
     estable
    1.07
     actually
    1.05
    actually
    1.05
    Activations Density 0.013%

    No Known Activations