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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10303
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with '2'

    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
     Curling
    -1.38
     مشاور
    -1.30
    ㇼ
    -1.29
    》《
    -1.27
    在她
    -1.26
    Doesn
    -1.26
    きら
    -1.23
    ็จ
    -1.23
    used
    -1.21
     KIN
    -1.21
    POSITIVE LOGITS
     would
    1.66
     natomiast
    1.49
    ↵↵
    1.47
     three
    1.40
     two
    1.38
     people
    1.38
     are
    1.37
    jährige
    1.31
     four
    1.30
     having
    1.27
    Activations Density 0.036%

    No Known Activations