© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     praticamente
    -1.98
     otorga
    -1.95
     Não
    -1.95
     promove
    -1.85
     proporciona
    -1.84
    摸了
    -1.78
     geralmente
    -1.77
     garantiza
    -1.76
     focuses
    -1.69
     generazione
    -1.68
    POSITIVE LOGITS
     invigor
    2.17
     as
    2.13
    </sub>
    2.13
     rejuven
    1.94
    </h3>
    1.92
     still
    1.89
     cleverly
    1.87
     enormous
    1.84
     excessively
    1.84
     subtly
    1.82
    Activations Density 0.072%

    No Known Activations