© 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. 105883
    Prev
    Next
    INDEX
    Explanations

    bubble

    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
    矬
    -2.98
    泐
    -2.75
    腚
    -2.70
     occuper
    -2.69
    commonly
    -2.66
     unbelievably
    -2.55
     daje
    -2.55
    のよう
    -2.53
     insanely
    -2.48
     ステン
    -2.48
    POSITIVE LOGITS
    d
    4.00
    e
    2.97
    o
    2.59
    ;
    2.55
    c
    2.55
     hesitant
    2.53
      
    2.47
    外的
    2.31
    That
    2.31
    :
    2.27
    Activations Density 0.002%

    No Known Activations