© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100738
    Prev
    Next
    INDEX
    Explanations

    certainly followed by other words

    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
     and
    -2.03
     eléctricas
    -1.82
     instruk
    -1.70
     stuks
    -1.70
     listos
    -1.66
     acheté
    -1.65
     ekran
    -1.59
     bluz
    -1.59
    AJ
    -1.57
     katalog
    -1.57
    POSITIVE LOGITS
     when
    1.99
     some
    1.84
     because
    1.83
     that
    1.82
     these
    1.78
    álbum
    1.70
    for
    1.63
    that
    1.57
    ’
    1.54
    swire
    1.50
    Activations Density 0.005%

    No Known Activations