© 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. 71677
    Prev
    Next
    INDEX
    Explanations

    needs more work or improvement

    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
    这类
    -1.38
    wyt
    -1.37
     sindic
    -1.30
    dì
    -1.26
    footnote
    -1.26
     cerrado
    -1.25
     you
    -1.24
     brinde
    -1.22
     ดู
    -1.22
     dà
    -1.22
    POSITIVE LOGITS
     and
    1.42
    新的
    1.40
     until
    1.33
     their
    1.33
     acrob
    1.26
     Giugno
    1.25
     chocol
    1.23
     as
    1.23
     zahlreiche
    1.23
     applic
    1.19
    Activations Density 0.029%

    No Known Activations