© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69863
    Prev
    Next
    INDEX
    Explanations

    carton, catenin, Bauer

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

    words related to packaging or containers, particularly "carton" and related terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     l
    -2.98
     =
    -2.80
     в
    -2.77
     {
    -2.67
    C
    -2.58
    و
    -2.56
    U
    -2.56
    se
    -2.48
     o
    -2.48
     le
    -2.44
    POSITIVE LOGITS
    谖
    3.00
    瓩
    2.94
    盌
    2.88
    ſelves
    2.78
    镚
    2.78
    他们在
    2.77
    ਞ
    2.75
    猡
    2.70
    鸸
    2.70
     když
    2.66
    Activations Density 0.018%

    No Known Activations