© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 649
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
    enablog
    -1.75
    на
    -1.62
    違います
    -1.60
     define
    -1.60
    asions
    -1.53
    があります
    -1.51
    は
    -1.49
     喜欢
    -1.48
    ᠊
    -1.41
    ільки
    -1.38
    POSITIVE LOGITS
    such
    1.63
    ”),
    1.45
     desideri
    1.42
    毟
    1.38
     który
    1.36
    自己
    1.33
     continúas
    1.33
    regierung
    1.32
     SUCH
    1.32
     なる
    1.32
    Activations Density 0.218%

    No Known Activations