© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68026
    Prev
    Next
    INDEX
    Explanations

    proper names and entities

    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
     faſt
    -3.67
    ᯾
    -3.25
    殽
    -2.80
    蚡
    -2.63
    镡
    -2.61
    鸱
    -2.58
    幛
    -2.56
    牁
    -2.47
    橚
    -2.45
    意味着
    -2.42
    POSITIVE LOGITS
    {
    2.80
    o
    2.73
     經典
    2.67
    瑧
    2.63
    纮
    2.48
    瑨
    2.47
     燈
    2.45
    個月
    2.45
     мне
    2.41
     большая
    2.38
    Activations Density 0.001%

    No Known Activations