© 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. 10576
    Prev
    Next
    INDEX
    Explanations

    hand or hands

    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
    sibile
    -1.45
     adanya
    -1.45
     مسابقات
    -1.39
    ırken
    -1.37
    sibili
    -1.36
    -1.34
    ｽ
    -1.32
     Those
    -1.27
    ...
    -1.26
     девочек
    -1.25
    POSITIVE LOGITS
     belangrij
    1.56
    
    1.50
    ꜆
    1.43
    Ᏻ
    1.42
    
    1.40
    廰
    1.40
    癭
    1.39
    懨
    1.39
    縂
    1.38
     различных
    1.36
    Activations Density 0.012%

    No Known Activations