© 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. 104787
    Prev
    Next
    INDEX
    Explanations

    nothing + [verb/assertion]

    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
     también
    -2.16
    Also
    -1.79
     também
    -1.78
     also
    -1.67
    also
    -1.56
     også
    -1.53
     أيضا
    -1.51
     still
    -1.50
     גם
    -1.45
     papir
    -1.42
    POSITIVE LOGITS
     zuvor
    1.80
     prevista
    1.50
    就没有
    1.42
     これ
    1.41
     I
    1.41
     keinerlei
    1.39
    した後
    1.38
    媼
    1.38
    ayanan
    1.38
     sonst
    1.38
    Activations Density 0.103%

    No Known Activations