© 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. 7460
    Prev
    Next
    INDEX
    Explanations

    athletes, musicians, actors

    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
     洗濯
    -2.00
    谖
    -1.95
    0
    -1.95
     impediments
    -1.70
     compréhension
    -1.70
    1
    -1.70
     самая
    -1.69
    3
    -1.68
     unwillingness
    -1.63
    9
    -1.60
    POSITIVE LOGITS
    丄
    1.74
    煨
    1.63
    鹇
    1.63
    {
    1.55
    时代
    1.55
    esters
    1.55
    用に
    1.55
    имость
    1.54
    actéristi
    1.52
    原始内容存档于
    1.50
    Activations Density 0.009%

    No Known Activations