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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119882
    Prev
    Next
    INDEX
    Explanations

    malnutrition, scriptures, GTA

    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
    涠
    -3.06
    舠
    -2.92
    沕
    -2.92
    猡
    -2.86
    身后的
    -2.80
     fiume
    -2.77
    乸
    -2.75
     emporio
    -2.72
    鼇
    -2.70
    镡
    -2.66
    POSITIVE LOGITS
    er
    3.13
    X
    2.91
     
    2.78
    N
    2.75
    li
    2.72
    ro
    2.70
    ise
    2.67
    f
    2.67
    led
    2.67
    ha
    2.67
    Activations Density 0.009%

    No Known Activations