© 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. 11032
    Prev
    Next
    INDEX
    Explanations

    drawer or drawers

    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
    {
    -1.96
    6
    -1.82
    2
    -1.73
    1
    -1.69
    *
    -1.67
    "
    -1.67
     完了
    -1.67
    $
    -1.66
    3
    -1.63
     zorro
    -1.53
    POSITIVE LOGITS
    あります
    1.96
    ضيف
    1.87
     drawer
    1.84
     impoverished
    1.84
    ୪
    1.81
     drawers
    1.77
    υμα
    1.77
    MockBean
    1.76
     torment
    1.75
     eerder
    1.75
    Activations Density 0.006%

    No Known Activations