© 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. 104999
    Prev
    Next
    INDEX
    Explanations

    s3 bucket and bitbucket

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

    the word "bucket" in technical contexts, particularly related to AWS S3 buckets and data storage.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on mentions of “bucket” (e.g. S3 or storage bucket references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    1
    -2.88
     biografia
    -2.30
     zusätzlichen
    -2.14
     Gefühle
    -2.14
    㩒
    -2.11
     huf
    -2.09
    
    -2.09
     ausein
    -2.09
     gearbeitet
    -2.08
     trovo
    -2.08
    POSITIVE LOGITS
    <bos>
    3.25
     
    3.14
     Both
    2.70
     hacer
    2.16
    鸰
    2.13
     madura
    2.11
     After
    2.08
    此人
    2.06
    medriver
    2.05
     sowohl
    1.99
    Activations Density 0.001%

    No Known Activations