© 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. 9794
    Prev
    Next
    INDEX
    Explanations

    words starting with "Mal"

    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
    身边的
    -2.97
    笮
    -2.94
    
    -2.72
    もしっかり
    -2.66
     mutlu
    -2.61
    腚
    -2.53
    晢
    -2.50
     срока
    -2.47
    有一定的
    -2.47
     andern
    -2.45
    POSITIVE LOGITS
    1
    3.77
    e
    3.17
    7
    3.09
    5
    2.81
    3
    2.80
    ４
    2.75
    就
    2.73
    8
    2.70
    2
    2.59
    ቬ
    2.59
    Activations Density 0.027%

    No Known Activations