© 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. 75646
    Prev
    Next
    INDEX
    Explanations

    parenthetical numbers or quantities

    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
     During
    -2.59
     one
    -2.47
     three
    -2.36
     When
    -2.34
     slight
    -2.33
     Two
    -2.31
    geſ
    -2.31
    0
    -2.25
     two
    -2.16
     eight
    -2.16
    POSITIVE LOGITS
     включая
    2.33
    zości
    2.30
     '
    2.28
     is
    2.09
    」、「
    2.03
     diarios
    2.02
     continúas
    2.02
    ться
    2.00
     другим
    2.00
     nieuwe
    1.99
    Activations Density 0.207%

    No Known Activations