© 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. 19943
    Prev
    Next
    INDEX
    Explanations

    Enron contracts and dealings

    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
    7
    -2.22
    9
    -2.11
    8
    -2.00
    5
    -1.98
     does
    -1.79
    0
    -1.79
     will
    -1.78
    4
    -1.77
    2
    -1.74
     cannot
    -1.73
    POSITIVE LOGITS
     bezpeč
    1.72
    箧
    1.69
     SUCH
    1.66
     kompati
    1.65
    쫑
    1.59
     EVEN
    1.59
     his
    1.58
    鴞
    1.57
    aient
    1.56
     miniaturka
    1.56
    Activations Density 0.014%

    No Known Activations