© 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. 13749
    Prev
    Next
    INDEX
    Explanations

    credit or credits

    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
     awakeFromNib
    -1.48
     quieres
    -1.46
    3
    -1.45
    1
    -1.43
    ínguez
    -1.40
     he
    -1.39
     literally
    -1.37
    全都
    -1.33
    、“
    -1.32
     cinta
    -1.30
    POSITIVE LOGITS
     清新
    1.47
     semelh
    1.46
    following
    1.46
     suscit
    1.45
    CHANG
    1.45
    おわりに
    1.43
    ーと
    1.41
    此人
    1.38
     データ
    1.38
     ภาพ
    1.36
    Activations Density 0.029%

    No Known Activations