© 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. 21870
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "without the"

    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
     by
    -2.41
     still
    -2.03
     sicheren
    -1.95
     on
    -1.90
     despite
    -1.79
     Preisen
    -1.77
    because
    -1.76
     because
    -1.74
    ensement
    -1.73
     well
    -1.73
    POSITIVE LOGITS
    尨
    1.98
     adicional
    1.94
    辚
    1.91
     necessarily
    1.87
    idopsis
    1.85
     attendant
    1.85
    驺
    1.77
    蹕
    1.77
     undue
    1.76
    </strong>
    1.72
    Activations Density 0.019%

    No Known Activations