© 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. 74772
    Prev
    Next
    INDEX
    Explanations

    "A"

    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
    窳
    -1.48
    龃
    -1.41
    
    -1.39
    蒾
    -1.38
    alisco
    -1.34
    kumpulan
    -1.33
    蕻
    -1.33
    IENTE
    -1.33
     ním
    -1.32
    🅂
    -1.31
    POSITIVE LOGITS
     but
    1.98
    You
    1.75
    .
    1.58
    ="
    1.51
    其他
    1.44
    open
    1.39
     mittleren
    1.38
    存在
    1.36
     Sélectionnez
    1.33
     Souhaitez
    1.33
    Activations Density 0.064%

    No Known Activations