© 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. 34-GEMMASCOPE-RES-131K
    7. 73451
    Prev
    Next
    INDEX
    Explanations

    doesn't + 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_34/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
    鹩
    -1.57
    紲
    -1.52
    刄
    -1.48
    킁
    -1.47
     pourront
    -1.47
     puissent
    -1.47
     efekty
    -1.45
     constater
    -1.41
     burbu
    -1.41
    ícias
    -1.38
    POSITIVE LOGITS
     have
    2.55
     seem
    2.08
     know
    1.92
     want
    1.84
     need
    1.70
     even
    1.64
    H
    1.57
     offer
    1.55
     belong
    1.55
     really
    1.50
    Activations Density 0.047%

    No Known Activations