© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99676
    Prev
    Next
    INDEX
    Explanations

    names of spouses

    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
     just
    -1.83
     all
    -1.71
     their
    -1.56
    rías
    -1.55
     its
    -1.51
     where
    -1.42
     even
    -1.33
     trekken
    -1.32
    來的
    -1.32
     contenuti
    -1.31
    POSITIVE LOGITS
    kere
    1.30
     คือ
    1.30
    romeda
    1.30
    kende
    1.29
     ท
    1.25
    owing
    1.25
     ambiental
    1.24
    orra
    1.24
     usados
    1.24
     พ
    1.23
    Activations Density 0.032%

    No Known Activations