© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68428
    Prev
    Next
    INDEX
    Explanations

    aws s3 and lambda operations

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

    The neuron activates on mentions of the AWS S3 service (e.g. “s3,” “boto3,” “aws-cli,” “moto”) and related SDK/CLI 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
    ⚋
    -1.86
    4
    -1.82
     charmant
    -1.81
    岨
    -1.77
    厹
    -1.76
     Erwartungen
    -1.76
     pleaſure
    -1.72
    7
    -1.71
    ことの
    -1.70
    泐
    -1.70
    POSITIVE LOGITS
     was
    1.80
     must
    1.79
     There
    1.73
     is
    1.71
    I
    1.59
     What
    1.58
     and
    1.56
     gets
    1.55
    Aunque
    1.49
    で
    1.48
    Activations Density 0.010%

    No Known Activations