© 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. 66522
    Prev
    Next
    INDEX
    Explanations

    ada sequence in names and places

    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
    妧
    -2.67
    幷
    -2.67
    廰
    -2.64
    mountable
    -2.64
    ޝ
    -2.59
    麁
    -2.59
    酲
    -2.55
    ޞ
    -2.55
    我现在
    -2.53
    褔
    -2.47
    POSITIVE LOGITS
    ada
    4.44
    на
    2.83
     
    2.81
    ↵↵
    2.75
    adas
    2.70
    t
    2.69
    ADA
    2.64
    d
    2.58
    在他
    2.53
    -
    2.36
    Activations Density 0.005%

    No Known Activations