© 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. 820
    Prev
    Next
    INDEX
    Explanations

    code diffs and imports

    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
     motocicletas
    -1.86
     tentang
    -1.75
     bagaimana
    -1.66
     fabricar
    -1.56
     –
    -1.54
    Despite
    -1.54
     and
    -1.53
     equipaje
    -1.52
    ’:
    -1.52
     mercancías
    -1.51
    POSITIVE LOGITS
     of
    2.00
     $
    1.68
     the
    1.54
     帅气
    1.49
     schuldig
    1.48
    abstractmethod
    1.45
    の説明
    1.43
    性の
    1.41
     schermata
    1.41
     été
    1.41
    Activations Density 0.000%

    No Known Activations