© 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. 123608
    Prev
    Next
    INDEX
    Explanations

    temporal adverbs and entities

    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
     також
    -1.66
    also
    -1.59
     también
    -1.53
     also
    -1.52
     także
    -1.50
     també
    -1.44
     também
    -1.41
     также
    -1.39
     również
    -1.38
     też
    -1.37
    POSITIVE LOGITS
     their
    1.34
     pneus
    1.16
     maintenant
    1.10
     now
    1.10
     şimdi
    1.09
    `;
    1.06
    beleid
    1.05
     warum
    1.05
     сейчас
    1.04
     actuellement
    1.02
    Activations Density 0.182%

    No Known Activations