© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112698
    Prev
    Next
    INDEX
    Explanations

    industry

    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_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
    焄
    -1.92
     که
    -1.91
    本当の
    -1.72
    慊
    -1.72
    mbangkan
    -1.68
    𐐪
    -1.63
    比如说
    -1.60
    ᨆ
    -1.59
    ꜆
    -1.59
    
    -1.59
    POSITIVE LOGITS
    "
    2.17
     industry
    2.05
    He
    1.83
     industries
    1.83
    it
    1.82
     sectors
    1.81
     diesem
    1.80
    .
    1.79
    wide
    1.74
    le
    1.70
    Activations Density 0.025%

    No Known Activations