© 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. 20793
    Prev
    Next
    INDEX
    Explanations

    able to

    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
     '
    -2.03
    倀
    -1.65
    Màu
    -1.57
    裟
    -1.53
    不由得
    -1.48
     '[
    -1.45
     &
    -1.42
    大きい
    -1.40
     as
    -1.37
    ப்பட்டது
    -1.37
    POSITIVE LOGITS
    that
    1.55
     καὶ
    1.46
    孩子的
    1.45
     unable
    1.39
    <h4>
    1.37
     рассказывает
    1.34
    That
    1.33
       
    1.32
    र्स
    1.32
     ready
    1.31
    Activations Density 0.045%

    No Known Activations