© 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. 111138
    Prev
    Next
    INDEX
    Explanations

    is a/an/the explanation

    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
     моей
    -2.09
     моих
    -1.83
    zembro
    -1.73
     моего
    -1.71
    宬
    -1.69
    carnation
    -1.62
    trois
    -1.61
     каждом
    -1.55
    zember
    -1.55
     вижу
    -1.52
    POSITIVE LOGITS
     the
    3.08
     a
    2.72
     an
    1.81
     ollut
    1.71
     tärke
    1.66
     when
    1.64
     another
    1.51
     Previously
    1.48
    '
    1.47
    туру
    1.41
    Activations Density 0.032%

    No Known Activations