© 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. 73159
    Prev
    Next
    INDEX
    Explanations

    Albuquerque and newbie concepts

    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
    {
    -2.67
     toughest
    -2.42
     unor
    -2.31
    驀
    -2.27
    肫
    -2.25
     usual
    -2.23
    美国的
    -2.22
     inaugural
    -2.19
     různých
    -2.17
    当下
    -2.16
    POSITIVE LOGITS
    遢
    3.03
    퐸
    2.59
    毐
    2.39
     Portugu
    2.28
     However
    2.25
    也有
    2.20
    緜
    2.20
     With
    2.19
     Until
    2.13
    一旁
    2.13
    Activations Density 0.004%

    No Known Activations