© 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. 72925
    Prev
    Next
    INDEX
    Explanations

    legal section marker

    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
    -2.95
     multitude
    -2.80
     unrelenting
    -2.63
    Maybe
    -2.53
    with
    -2.52
    They
    -2.45
    You
    -2.45
     Those
    -2.39
     With
    -2.34
     plethora
    -2.30
    POSITIVE LOGITS
    ра
    2.77
    te
    2.63
    ti
    2.55
     стал
    2.42
     reiter
    2.42
    ).
    2.41
     zwei
    2.41
     fünf
    2.39
    .,
    2.38
     famoso
    2.28
    Activations Density 0.003%

    No Known Activations