© 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. 48423
    Prev
    Next
    INDEX
    Explanations

    also followed by verb

    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
     also
    -1.91
     and
    -1.70
     bahkan
    -1.56
     moreover
    -1.52
    also
    -1.52
     Moreover
    -1.50
     además
    -1.48
    ť
    -1.40
    Also
    -1.38
     by
    -1.37
    POSITIVE LOGITS
     doká
    1.44
    が欲しい
    1.35
     caricatura
    1.31
     puentes
    1.29
     přístup
    1.27
     ویکی‌پدیا
    1.27
    髫
    1.27
     majú
    1.27
    いため
    1.26
     variados
    1.26
    Activations Density 0.036%

    No Known Activations